Heteroscedastic Laplace mixture of experts regression models and applications

Mixture of Experts(MoE)regression models are widely studied in statistics and machine learning for modeling heterogeneity in data for regression,clustering and classification.Laplace distribution is one of the most important statistical tools to analyze thick and tail data.Laplace Mixture of Linear Experts(LMoLE)regression models are based on the Laplace distribution which is more robust.Similar to modelling variance parameter in a homogeneous population,we propose and study a new novel class of models:heteroscedastic Laplace mixture of experts regression models to analyze the heteroscedastic data coming from a heterogeneous population in this paper.The issues of maximum likelihood estimation are addressed.In particular,Minorization-Maximization(MM)algorithm for estimating the regression parameters is developed.Properties of the estimators of the regression coefficients are evaluated through Monte Carlo simulations.Results from the analysis of two real data sets are presented.

A Latent Entity-Document Class Mixture of Experts Model for Cumulative Citation Recommendation

Knowledge Bases （KBs） are valuable resources of human knowledge which contribute to many applications. However, since they are manually maintained, there is a big lag between their contents and the upto-date information of entities. Considering a target entity in KBs, this paper investigates how Cumulative Citation Recommendation （CCR） can be used to effectively detect its worthy-citation documents in large volumes of stream data. Most global relevant models only consider semantic and temporat features of entity-document instances, which does not sufficiently exploit prior knowledge underlying entity-document instances. To tackle this problem, we present a Mixture of Experts （ME） model by introducing a latent layer to capture relationships between the entity-document instances and their latent class information. An extensive set of experiments was conducted on TREC-KBA-2013 dataset. The results show that the model can significantly achieve a better performance gain compared to state-of-the-art models in CCR.

Adaptive Multi-modal Fusion Instance Segmentation for CAEVs in Complex Conditions:Dataset,Framework and Verifications

Current works of environmental perception for connected autonomous electrified vehicles(CAEVs)mainly focus on the object detection task in good weather and illumination conditions,they often perform poorly in adverse scenarios and have a vague scene parsing ability.This paper aims to develop an end-to-end sharpening mixture of experts(SMoE)fusion framework to improve the robustness and accuracy of the perception systems for CAEVs in complex illumination and weather conditions.Three original contributions make our work distinctive from the existing relevant literature.The Complex KITTI dataset is introduced which consists of 7481 pairs of modified KITTI RGB images and the generated LiDAR dense depth maps,and this dataset is fine annotated in instance-level with the proposed semi-automatic annotation method.The SMoE fusion approach is devised to adaptively learn the robust kernels from complementary modalities.Comprehensive comparative experiments are implemented,and the results show that the proposed SMoE framework yield significant improvements over the other fusion techniques in adverse environmental conditions.This research proposes a SMoE fusion framework to improve the scene parsing ability of the perception systems for CAEVs in adverse conditions.

Space-time video super-resolution using long-term temporal feature aggregation

Space-time video super-resolution(STVSR)serves the purpose to reconstruct high-resolution high-frame-rate videos from their low-resolution low-frame-rate counterparts.Recent approaches utilize end-to-end deep learning models to achieve STVSR.They first interpolate intermediate frame features between given frames,then perform local and global refinement among the feature sequence,and finally increase the spatial resolutions of these features.However,in the most important feature interpolation phase,they only capture spatial-temporal information from the most adjacent frame features,ignoring modelling long-term spatial-temporal correlations between multiple neighbouring frames to restore variable-speed object movements and maintain long-term motion continuity.In this paper,we propose a novel long-term temporal feature aggregation network(LTFA-Net)for STVSR.Specifically,we design a long-term mixture of experts(LTMoE)module for feature interpolation.LTMoE contains multiple experts to extract mutual and complementary spatial-temporal information from multiple consecutive adjacent frame features,which are then combined with different weights to obtain interpolation results using several gating nets.Next,we perform local and global feature refinement using the Locally-temporal Feature Comparison(LFC)module and bidirectional deformable ConvLSTM layer,respectively.Experimental results on two standard benchmarks,Adobe240 and GoPro,indicate the effectiveness and superiority of our approach over state of the art.

Improving Multi-task GNNs for Molecular Property Prediction via Missing Label Imputation

The prediction of molecular properties is a fundamental task in the field of drug discovery.Recently,graph neural networks(GNNs)have been gaining prominence in this area.Since a molecule tends to have multiple correlated properties,there is a great need to develop the multi-task learning ability of GNNs.However,limited by expensive and time-consuming human annotations,collecting complete labels for each task is difficult.As a result,most existing benchmarks involve many missing labels in training data,and the performance of GNNs is impaired due to the lack of sufficient supervision information.To overcome this obstacle,we propose to improve multi-task molecular property prediction by missing label imputation.Specifically,a bipartite graph is first introduced to model the molecule-task co-occurrence relationships.Then,the imputation of missing labels is transformed into predicting missing edges on this bipartite graph.To predict the missing edges,a graph neural network is devised,which can learn the complex molecule-task co-occurrence relationships.After that,we select reliable pseudo labels according to the uncertainty of the prediction results.Boosting with enough and reliable supervision information,our approach achieves state-of-the-art performance on a variety of real-world datasets.