Let G be a graph and k≥2 a positive integer. Let h : E(G)→[0, 1] be a function. If e∑eЭxh(e) = k holds for each x∈V(G), then we call G[Fh ] a fractional k-factor of G with indicator function h where Fh ={e...Let G be a graph and k≥2 a positive integer. Let h : E(G)→[0, 1] be a function. If e∑eЭxh(e) = k holds for each x∈V(G), then we call G[Fh ] a fractional k-factor of G with indicator function h where Fh ={e∈E(G) : h(e) 〉 0}. A graph G is fractional independent-set-deletable k-factor-critical(in short, fractional ID-k-factor-critical), if G-I has a fractional k-factor for every independent set I of G. In this paper, we prove that if n≥9 k-14 and for any subset X?V(G) we have NG(X) = V(G) if |X| ≥ kn/(3k-1); or |NG(X)3 k-1/k| ≥|X|if|X|〈 kn/(3k-1),then G is fractional ID-k-factor-critical.展开更多
A connected graph G is said to be a factor-critical graph if G - v has a perfect matching for every vertex v of G. In this paper, the 2-connected factor-critical graph G which has exactly |E(G)|+ 1 maximum matchi...A connected graph G is said to be a factor-critical graph if G - v has a perfect matching for every vertex v of G. In this paper, the 2-connected factor-critical graph G which has exactly |E(G)|+ 1 maximum matchings is characterized.展开更多
A graph G is said to be p-factor-critical if G-u1-u2-···-up has a perfect matching for any u1,u2,···,up∈V(G).The concept of p-factor-critical is a generalization of the concepts of facto...A graph G is said to be p-factor-critical if G-u1-u2-···-up has a perfect matching for any u1,u2,···,up∈V(G).The concept of p-factor-critical is a generalization of the concepts of factor-critical and bicritical for p=1 and p=2,respectively.Heping Zhang and Fuji Zhang[Construction for bicritical graphs and k-extendable bipartite graphs,Discrete Math.,306(2006)1415–1423]gave a concise structure characterization of bicritical graphs.In this paper,we present the characterizations of p-factor-critical graphs and minimal p-factorcritical graphs for p≥2.As an application,we also obtain a class of graphs which are minimal p-factor-critical for p≥1.展开更多
It is said that a graph G is independent-set-deletable factor-critical (in short, ID-factor-critical), if, for everyindependent-set I which has the same parity as |V(G)|, G - I has a perfect matching. A graph G ...It is said that a graph G is independent-set-deletable factor-critical (in short, ID-factor-critical), if, for everyindependent-set I which has the same parity as |V(G)|, G - I has a perfect matching. A graph G is strongly IM-extendable, if for every spanning supergraph H of G, every induced matching of H is included in a perfect matching of H. The κ-th power of G, denoted by G^κ, is the graph with vertex set V(G) in which two vertices are adjacent if and only if they have distance at most k in G. ID-factor-criticality and IM-extendability of power graphs are discussed in this article. The author shows that, if G is a connected graph, then G^3 and T(G) (the total graph of G) are ID-factor-critical, and G^4 (when |V(G)| is even) is strongly IM-extendable; if G is 2-connected, then D^2 is ID-factor-critical.展开更多
Let G be a graph, and k a positive integer. A graph G is fractional independent-set-deletable k-factor-critical(in short, fractional ID-k-factor-critical) if G-I has a fractional k-factor for every independent set I o...Let G be a graph, and k a positive integer. A graph G is fractional independent-set-deletable k-factor-critical(in short, fractional ID-k-factor-critical) if G-I has a fractional k-factor for every independent set I of G. In this paper, we present a sufficient condition for a graph to be fractional ID-k-factor-critical,depending on the minimum degree and the neighborhoods of independent sets. Furthermore, it is shown that this result in this paper is best possible in some sense.展开更多
Let a, b, r be nonnegative integers with 1 ≤ a ≤ b and r ≥ 2. Let G be a graph of order n with n 〉(a+2 b)(r(a+b)-2)/b.In this paper, we prove that G is fractional ID-[a, b]-factor-critical if δ(G)≥bn/a...Let a, b, r be nonnegative integers with 1 ≤ a ≤ b and r ≥ 2. Let G be a graph of order n with n 〉(a+2 b)(r(a+b)-2)/b.In this paper, we prove that G is fractional ID-[a, b]-factor-critical if δ(G)≥bn/a+2 b+a(r-1)and |NG(x1) ∪ NG(x2) ∪…∪ NG(xr)| ≥(a+b)n/(a+2 b) for any independent subset {x1,x2,…,xr} in G. It is a generalization of Zhou et al.'s previous result [Discussiones Mathematicae Graph Theory, 36: 409-418(2016)]in which r = 2 is discussed. Furthermore, we show that this result is best possible in some sense.展开更多
The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to u...The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.展开更多
LetG be a graph,and k≥2 be a positive integer.A graph G is fractional independentset-deletable k-factor-critical(in short,fractional ID-k-factor-critical),if G I has a fractional k-factor for every independent set ...LetG be a graph,and k≥2 be a positive integer.A graph G is fractional independentset-deletable k-factor-critical(in short,fractional ID-k-factor-critical),if G I has a fractional k-factor for every independent set I of G.The binding number bind(G)of a graph G is defined as bind(G)=min|NG(X)||X|:=X V(G),NG(X)=V(G).In this paper,it is proved that a graph G is fractional ID-k-factor-critical if n≥6k 9 and bind(G)〉(3k 1)(n 1)kn 2k+2.展开更多
In this paper,we investigate spacelike graphs defined over a domain Ω⊂M^(n) in the Lorentz manifold M^(n)×ℝ with the metric−ds^(2)+σ,where M^(n) is a complete Riemannian n-manifold with the metricσ,Ωhas piece...In this paper,we investigate spacelike graphs defined over a domain Ω⊂M^(n) in the Lorentz manifold M^(n)×ℝ with the metric−ds^(2)+σ,where M^(n) is a complete Riemannian n-manifold with the metricσ,Ωhas piecewise smooth boundary,and ℝ denotes the Euclidean 1-space.We prove an interesting stability result for translating spacelike graphs in M^(n)×ℝ under a conformal transformation.展开更多
Given a graph g=( V,A ) , we define a space of subgraphs M with the binary operation of union and the unique decomposition property into blocks. This space allows us to discuss a notion of minimal subgraphs (minimal c...Given a graph g=( V,A ) , we define a space of subgraphs M with the binary operation of union and the unique decomposition property into blocks. This space allows us to discuss a notion of minimal subgraphs (minimal coalitions) that are of interest for the game. Additionally, a partition of the game is defined in terms of the gain of each block, and subsequently, a solution to the game is defined based on distributing to each player (node and edge) present in each block a payment proportional to their contribution to the coalition.展开更多
Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggre...Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggregation and embedding.However,in heterophilic graphs,nodes from different categories often establish connections,while nodes of the same category are located further apart in the graph topology.This characteristic poses challenges to traditional GNNs,leading to issues of“distant node modeling deficiency”and“failure of the homophily assumption”.In response,this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks(SFA-HGNN),which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned issues.Specifically,for the first problem,we propose the“Distant Spatial Embedding Module”,aiming to select and aggregate distant nodes through high-order randomwalk transition probabilities to enhance modeling capabilities.For the second issue,we design the“Proximal Frequency Domain Embedding Module”,constructing adaptive filters to separate high and low-frequency signals of nodes,and introduce frequency-domain guided attention mechanisms to fuse the relevant information,thereby reducing the noise introduced by the failure of the homophily assumption.We deploy the SFA-HGNN on six publicly available heterophilic networks,achieving state-of-the-art results in four of them.Furthermore,we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation,demonstrating a positive correlation between“node structural similarity”,“node attribute vector similarity”,and“node homophily”in heterophilic networks.展开更多
Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been ...Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.展开更多
Graph Convolutional Neural Networks(GCNs)have been widely used in various fields due to their powerful capabilities in processing graph-structured data.However,GCNs encounter significant challenges when applied to sca...Graph Convolutional Neural Networks(GCNs)have been widely used in various fields due to their powerful capabilities in processing graph-structured data.However,GCNs encounter significant challenges when applied to scale-free graphs with power-law distributions,resulting in substantial distortions.Moreover,most of the existing GCN models are shallow structures,which restricts their ability to capture dependencies among distant nodes and more refined high-order node features in scale-free graphs with hierarchical structures.To more broadly and precisely apply GCNs to real-world graphs exhibiting scale-free or hierarchical structures and utilize multi-level aggregation of GCNs for capturing high-level information in local representations,we propose the Hyperbolic Deep Graph Convolutional Neural Network(HDGCNN),an end-to-end deep graph representation learning framework that can map scale-free graphs from Euclidean space to hyperbolic space.In HDGCNN,we define the fundamental operations of deep graph convolutional neural networks in hyperbolic space.Additionally,we introduce a hyperbolic feature transformation method based on identity mapping and a dense connection scheme based on a novel non-local message passing framework.In addition,we present a neighborhood aggregation method that combines initial structural featureswith hyperbolic attention coefficients.Through the above methods,HDGCNN effectively leverages both the structural features and node features of graph data,enabling enhanced exploration of non-local structural features and more refined node features in scale-free or hierarchical graphs.Experimental results demonstrate that HDGCNN achieves remarkable performance improvements over state-ofthe-art GCNs in node classification and link prediction tasks,even when utilizing low-dimensional embedding representations.Furthermore,when compared to shallow hyperbolic graph convolutional neural network models,HDGCNN exhibits notable advantages and performance enhancements.展开更多
The growing prevalence of knowledge reasoning using knowledge graphs(KGs)has substantially improved the accuracy and efficiency of intelligent medical diagnosis.However,current models primarily integrate electronic me...The growing prevalence of knowledge reasoning using knowledge graphs(KGs)has substantially improved the accuracy and efficiency of intelligent medical diagnosis.However,current models primarily integrate electronic medical records(EMRs)and KGs into the knowledge reasoning process,ignoring the differing significance of various types of knowledge in EMRs and the diverse data types present in the text.To better integrate EMR text information,we propose a novel intelligent diagnostic model named the Graph ATtention network incorporating Text representation in knowledge reasoning(GATiT),which comprises text representation,subgraph construction,knowledge reasoning,and diagnostic classification.In the text representation process,GATiT uses a pre-trained model to obtain text representations of the EMRs and additionally enhances embeddings by including chief complaint information and numerical information in the input.In the subgraph construction process,GATiT constructs text subgraphs and disease subgraphs from the KG,utilizing EMR text and the disease to be diagnosed.To differentiate the varying importance of nodes within the subgraphs features such as node categories,relevance scores,and other relevant factors are introduced into the text subgraph.Themessage-passing strategy and attention weight calculation of the graph attention network are adjusted to learn these features in the knowledge reasoning process.Finally,in the diagnostic classification process,the interactive attention-based fusion method integrates the results of knowledge reasoning with text representations to produce the final diagnosis results.Experimental results on multi-label and single-label EMR datasets demonstrate the model’s superiority over several state-of-theart methods.展开更多
The selection of chemical reactions is directly related to the quality of synthesis pathways,so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways.Since react...The selection of chemical reactions is directly related to the quality of synthesis pathways,so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways.Since reaction conditions also need to be considered in synthesis pathway design,a reaction metric that combines reaction time,temperature,and yield is required for chemical reactions of different reaction agents.In this study,a chemical reaction graph descriptor which includes the atom-atom mapping relationship is proposed to effectively describe reactions.Then,through pre-training using graph contrastive learning and fine-tuning through supervised learning,we establish a model for generating the probability of reaction superiority(RSscore).Finally,to validate the effectiveness of the current evaluation index,RSscore is applied in two applications,namely reaction evaluation and synthesis routes analysis,which proves that the RSscore provides an important agents-considered evaluation criterion for computer-aided synthesis planning(CASP).展开更多
Let R be a commutative ring with identity and M an R-module. In this paper, we relate a graph to M, say Γ(M), provided tsshat when M=R, Γ(M)is exactly the classic zero-divisor graph.
基金sponsored by the National Natural Science Foundation of China(Grant No.11371009,11501256,61503160)the National Social Science Foundation of China(Grant No.11BGL039)+1 种基金Six Big Talent Peak of Jiangsu Province(Grant No.JY–022)333 Project of Jiangsu Province
文摘Let G be a graph and k≥2 a positive integer. Let h : E(G)→[0, 1] be a function. If e∑eЭxh(e) = k holds for each x∈V(G), then we call G[Fh ] a fractional k-factor of G with indicator function h where Fh ={e∈E(G) : h(e) 〉 0}. A graph G is fractional independent-set-deletable k-factor-critical(in short, fractional ID-k-factor-critical), if G-I has a fractional k-factor for every independent set I of G. In this paper, we prove that if n≥9 k-14 and for any subset X?V(G) we have NG(X) = V(G) if |X| ≥ kn/(3k-1); or |NG(X)3 k-1/k| ≥|X|if|X|〈 kn/(3k-1),then G is fractional ID-k-factor-critical.
基金supported by the National Natural Science Foundation of China(No.11551003)the Scientific research fund of the Science and Technology Program of Guangzhou,China(No.201510010265)the Qinghai Province Natural Science Foundation(No.2015-ZJ-911)
文摘A connected graph G is said to be a factor-critical graph if G - v has a perfect matching for every vertex v of G. In this paper, the 2-connected factor-critical graph G which has exactly |E(G)|+ 1 maximum matchings is characterized.
基金Supported by the National Natural Science Foundation of China(No.11401576)。
文摘A graph G is said to be p-factor-critical if G-u1-u2-···-up has a perfect matching for any u1,u2,···,up∈V(G).The concept of p-factor-critical is a generalization of the concepts of factor-critical and bicritical for p=1 and p=2,respectively.Heping Zhang and Fuji Zhang[Construction for bicritical graphs and k-extendable bipartite graphs,Discrete Math.,306(2006)1415–1423]gave a concise structure characterization of bicritical graphs.In this paper,we present the characterizations of p-factor-critical graphs and minimal p-factorcritical graphs for p≥2.As an application,we also obtain a class of graphs which are minimal p-factor-critical for p≥1.
基金Project supported by NSFC(10371112)NSFHN (0411011200)SRF for ROCS,SEM
文摘It is said that a graph G is independent-set-deletable factor-critical (in short, ID-factor-critical), if, for everyindependent-set I which has the same parity as |V(G)|, G - I has a perfect matching. A graph G is strongly IM-extendable, if for every spanning supergraph H of G, every induced matching of H is included in a perfect matching of H. The κ-th power of G, denoted by G^κ, is the graph with vertex set V(G) in which two vertices are adjacent if and only if they have distance at most k in G. ID-factor-criticality and IM-extendability of power graphs are discussed in this article. The author shows that, if G is a connected graph, then G^3 and T(G) (the total graph of G) are ID-factor-critical, and G^4 (when |V(G)| is even) is strongly IM-extendable; if G is 2-connected, then D^2 is ID-factor-critical.
基金supported by the National Natural Science Foundation of China(Grant No.11371009,11501256,61503160)Six Big Talent Peak of Jiangsu Province(Grant No.JY–022)+3 种基金333 Project of Jiangsu Provincethe National Social Science Foundation of China(Grant No.14AGL001)the Natural Science Foundation of Xinjiang Province of China(Grant No.2015211A003)the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province(Grant No.14KJD110002)
文摘Let G be a graph, and k a positive integer. A graph G is fractional independent-set-deletable k-factor-critical(in short, fractional ID-k-factor-critical) if G-I has a fractional k-factor for every independent set I of G. In this paper, we present a sufficient condition for a graph to be fractional ID-k-factor-critical,depending on the minimum degree and the neighborhoods of independent sets. Furthermore, it is shown that this result in this paper is best possible in some sense.
基金supported by the National Natural Science Foundation of China(Nos.11371052,11731002)the Fundamental Research Funds for the Central Universities(Nos.2016JBM071,2016JBZ012)the 111 Project of China(B16002)
文摘Let a, b, r be nonnegative integers with 1 ≤ a ≤ b and r ≥ 2. Let G be a graph of order n with n 〉(a+2 b)(r(a+b)-2)/b.In this paper, we prove that G is fractional ID-[a, b]-factor-critical if δ(G)≥bn/a+2 b+a(r-1)and |NG(x1) ∪ NG(x2) ∪…∪ NG(xr)| ≥(a+b)n/(a+2 b) for any independent subset {x1,x2,…,xr} in G. It is a generalization of Zhou et al.'s previous result [Discussiones Mathematicae Graph Theory, 36: 409-418(2016)]in which r = 2 is discussed. Furthermore, we show that this result is best possible in some sense.
文摘The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.
基金Supported by Natural Science Foundation of the Higher Education Institutions of Jiangsu Province(Grant No.10KJB110003)Jiangsu University of Science and Technology(Grant No.2010SL101J)+1 种基金National Natural Science Foundation of China(Grant No.71271119)National Social Science Foundation of China(Grant No.11BGL039)
文摘LetG be a graph,and k≥2 be a positive integer.A graph G is fractional independentset-deletable k-factor-critical(in short,fractional ID-k-factor-critical),if G I has a fractional k-factor for every independent set I of G.The binding number bind(G)of a graph G is defined as bind(G)=min|NG(X)||X|:=X V(G),NG(X)=V(G).In this paper,it is proved that a graph G is fractional ID-k-factor-critical if n≥6k 9 and bind(G)〉(3k 1)(n 1)kn 2k+2.
基金supported in part by the NSFC(11801496,11926352)the Fok Ying-Tung Education Foundation(China)the Hubei Key Laboratory of Applied Mathematics(Hubei University).
文摘In this paper,we investigate spacelike graphs defined over a domain Ω⊂M^(n) in the Lorentz manifold M^(n)×ℝ with the metric−ds^(2)+σ,where M^(n) is a complete Riemannian n-manifold with the metricσ,Ωhas piecewise smooth boundary,and ℝ denotes the Euclidean 1-space.We prove an interesting stability result for translating spacelike graphs in M^(n)×ℝ under a conformal transformation.
文摘Given a graph g=( V,A ) , we define a space of subgraphs M with the binary operation of union and the unique decomposition property into blocks. This space allows us to discuss a notion of minimal subgraphs (minimal coalitions) that are of interest for the game. Additionally, a partition of the game is defined in terms of the gain of each block, and subsequently, a solution to the game is defined based on distributing to each player (node and edge) present in each block a payment proportional to their contribution to the coalition.
基金supported by the Fundamental Research Funds for the Central Universities(Grant No.2022JKF02039).
文摘Graph Neural Networks(GNNs)play a significant role in tasks related to homophilic graphs.Traditional GNNs,based on the assumption of homophily,employ low-pass filters for neighboring nodes to achieve information aggregation and embedding.However,in heterophilic graphs,nodes from different categories often establish connections,while nodes of the same category are located further apart in the graph topology.This characteristic poses challenges to traditional GNNs,leading to issues of“distant node modeling deficiency”and“failure of the homophily assumption”.In response,this paper introduces the Spatial-Frequency domain Adaptive Heterophilic Graph Neural Networks(SFA-HGNN),which integrates adaptive embedding mechanisms for both spatial and frequency domains to address the aforementioned issues.Specifically,for the first problem,we propose the“Distant Spatial Embedding Module”,aiming to select and aggregate distant nodes through high-order randomwalk transition probabilities to enhance modeling capabilities.For the second issue,we design the“Proximal Frequency Domain Embedding Module”,constructing adaptive filters to separate high and low-frequency signals of nodes,and introduce frequency-domain guided attention mechanisms to fuse the relevant information,thereby reducing the noise introduced by the failure of the homophily assumption.We deploy the SFA-HGNN on six publicly available heterophilic networks,achieving state-of-the-art results in four of them.Furthermore,we elaborate on the hyperparameter selection mechanism and validate the performance of each module through experimentation,demonstrating a positive correlation between“node structural similarity”,“node attribute vector similarity”,and“node homophily”in heterophilic networks.
基金This work was supported by the Kyonggi University Research Grant 2022.
文摘Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.
基金supported by the National Natural Science Foundation of China-China State Railway Group Co.,Ltd.Railway Basic Research Joint Fund (Grant No.U2268217)the Scientific Funding for China Academy of Railway Sciences Corporation Limited (No.2021YJ183).
文摘Graph Convolutional Neural Networks(GCNs)have been widely used in various fields due to their powerful capabilities in processing graph-structured data.However,GCNs encounter significant challenges when applied to scale-free graphs with power-law distributions,resulting in substantial distortions.Moreover,most of the existing GCN models are shallow structures,which restricts their ability to capture dependencies among distant nodes and more refined high-order node features in scale-free graphs with hierarchical structures.To more broadly and precisely apply GCNs to real-world graphs exhibiting scale-free or hierarchical structures and utilize multi-level aggregation of GCNs for capturing high-level information in local representations,we propose the Hyperbolic Deep Graph Convolutional Neural Network(HDGCNN),an end-to-end deep graph representation learning framework that can map scale-free graphs from Euclidean space to hyperbolic space.In HDGCNN,we define the fundamental operations of deep graph convolutional neural networks in hyperbolic space.Additionally,we introduce a hyperbolic feature transformation method based on identity mapping and a dense connection scheme based on a novel non-local message passing framework.In addition,we present a neighborhood aggregation method that combines initial structural featureswith hyperbolic attention coefficients.Through the above methods,HDGCNN effectively leverages both the structural features and node features of graph data,enabling enhanced exploration of non-local structural features and more refined node features in scale-free or hierarchical graphs.Experimental results demonstrate that HDGCNN achieves remarkable performance improvements over state-ofthe-art GCNs in node classification and link prediction tasks,even when utilizing low-dimensional embedding representations.Furthermore,when compared to shallow hyperbolic graph convolutional neural network models,HDGCNN exhibits notable advantages and performance enhancements.
基金supported in part by the Science and Technology Innovation 2030-“New Generation of Artificial Intelligence”Major Project(No.2021ZD0111000)Henan Provincial Science and Technology Research Project(No.232102211039).
文摘The growing prevalence of knowledge reasoning using knowledge graphs(KGs)has substantially improved the accuracy and efficiency of intelligent medical diagnosis.However,current models primarily integrate electronic medical records(EMRs)and KGs into the knowledge reasoning process,ignoring the differing significance of various types of knowledge in EMRs and the diverse data types present in the text.To better integrate EMR text information,we propose a novel intelligent diagnostic model named the Graph ATtention network incorporating Text representation in knowledge reasoning(GATiT),which comprises text representation,subgraph construction,knowledge reasoning,and diagnostic classification.In the text representation process,GATiT uses a pre-trained model to obtain text representations of the EMRs and additionally enhances embeddings by including chief complaint information and numerical information in the input.In the subgraph construction process,GATiT constructs text subgraphs and disease subgraphs from the KG,utilizing EMR text and the disease to be diagnosed.To differentiate the varying importance of nodes within the subgraphs features such as node categories,relevance scores,and other relevant factors are introduced into the text subgraph.Themessage-passing strategy and attention weight calculation of the graph attention network are adjusted to learn these features in the knowledge reasoning process.Finally,in the diagnostic classification process,the interactive attention-based fusion method integrates the results of knowledge reasoning with text representations to produce the final diagnosis results.Experimental results on multi-label and single-label EMR datasets demonstrate the model’s superiority over several state-of-theart methods.
基金the financial support of the National Natural Science Foundation of China(22078041,22278053)Dalian High-level Talents Innovation Support Program(2021RQ105)the Fundamental Research Funds for China Central Universities(DUT22QN209,DUT22LAB608).
文摘The selection of chemical reactions is directly related to the quality of synthesis pathways,so a reasonable reaction evaluation metric plays a crucial role in the design and planning of synthesis pathways.Since reaction conditions also need to be considered in synthesis pathway design,a reaction metric that combines reaction time,temperature,and yield is required for chemical reactions of different reaction agents.In this study,a chemical reaction graph descriptor which includes the atom-atom mapping relationship is proposed to effectively describe reactions.Then,through pre-training using graph contrastive learning and fine-tuning through supervised learning,we establish a model for generating the probability of reaction superiority(RSscore).Finally,to validate the effectiveness of the current evaluation index,RSscore is applied in two applications,namely reaction evaluation and synthesis routes analysis,which proves that the RSscore provides an important agents-considered evaluation criterion for computer-aided synthesis planning(CASP).
文摘Let R be a commutative ring with identity and M an R-module. In this paper, we relate a graph to M, say Γ(M), provided tsshat when M=R, Γ(M)is exactly the classic zero-divisor graph.