Heterogeneous decentralised machine unlearning with seed model distillation

As some recent information security legislation endowed users with unconditional rights to be forgotten by any trained machine learning model,personalised IoT service pro-viders have to put unlearning functionality into their consideration.The most straight-forward method to unlearn users'contribution is to retrain the model from the initial state,which is not realistic in high throughput applications with frequent unlearning requests.Though some machine unlearning frameworks have been proposed to speed up the retraining process,they fail to match decentralised learning scenarios.A decentralised unlearning framework called heterogeneous decentralised unlearning framework with seed(HDUS)is designed,which uses distilled seed models to construct erasable en-sembles for all clients.Moreover,the framework is compatible with heterogeneous on-device models,representing stronger scalability in real-world applications.Extensive experiments on three real-world datasets show that our HDUS achieves state-of-the-art performance.

User Account Linkage Across Multiple Platforms with Location Data

Linking user accounts belonging to the same user across different platforms with location data has received significant attention,due to the popularization of GPS-enabled devices and the wide range of applications benefiting from user account linkage(e.g.,cross-platform user profiling and recommendation).Different from most existing studies which only focus on user account linkage across two platforms,we propose a novel model ULMP(i.e.,user account linkage across multiple platforms),with the goal of effectively and efficiently linking user accounts across multiple platforms with location data.Despite of the practical significance brought by successful user linkage across multiple platforms,this task is very challenging compared with the ones across two platforms.The major challenge lies in the fact that the number of user combinations shows an explosive growth with the increase of the number of platforms.To tackle the problem,a novel method GTkNN is first proposed to prune the search space by efficiently retrieving top-k candidate user accounts indexed with well-designed spatial and temporal index structures.Then,in the pruned space,a match score based on kernel density estimation combining both spatial and temporal information is designed to retrieve the linked user accounts.The extensive experiments conducted on four real-world datasets demonstrate the superiority of the proposed model ULMP in terms of both effectiveness and efficiency compared with the state-of-art methods.

An Efficient Framework for Multiple Subgraph Pattern Matching Models

With the popularity of storing large data graph in cloud, the emergence of subgraph pattern matching on a remote cloud has been inspired. Typically, subgraph pattern matching is defined in terms of subgraph isomorphism, which is an NP-complete problem and sometimes too strict to find useful matches in certain applications. And how to protect the privacy of data graphs in subgraph pattern matching without undermining matching results is an important concern. Thus, we propose a novel framework to achieve the privacy-preserving subgraph pattern matching in cloud. In order to protect the structural privacy in data graphs, we firstly develop a k-automorphism model based method. Additionally, we use a cost-model based label generalization method to protect label privacy in both data graphs and pattern graphs. During the generation of the k-automorphic graph, a large number of noise edges or vertices might be introduced to the original data graph. Thus, we use the outsourced graph, which is only a subset of a k-automorphic graph, to answer the subgraph pattern matching. The efficiency of the pattern matching process can be greatly improved in this way. Extensive experiments on real-world datasets demonstrate the high efficiency of our framework.