Timezone: »

Robust Graph Representation Learning via Neural Sparsification
Cheng Zheng · Bo Zong · Wei Cheng · Dongjin Song · Jingchao Ni · Wenchao Yu · Haifeng Chen · Wei Wang

Wed Jul 15 11:00 AM -- 11:45 AM & Wed Jul 15 10:00 PM -- 10:45 PM (PDT) @

Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection. Real-life graphs usually have complex information in the local neighborhood, where each node is described by a rich set of features and connects to dozens or even hundreds of neighbors. Despite the success of neighborhood aggregation in graph neural networks, task-irrelevant information is mixed into nodes' neighborhood, making learned models suffer from sub-optimal generalization performance. In this paper, we present NeuralSparse, a supervised graph sparsification technique that improves generalization power by learning to remove potentially task-irrelevant edges from input graphs. Our method takes both structural and non-structural information as input, utilizes deep neural networks to parameterize sparsification processes, and optimizes the parameters by feedback signals from downstream tasks. Under the NeuralSparse framework, supervised graph sparsification could seamlessly connect with existing graph neural networks for more robust performance. Experimental results on both benchmark and private datasets show that NeuralSparse can yield up to 7.2% improvement in testing accuracy when working with existing graph neural networks on node classification tasks.

Author Information

Cheng Zheng (UCLA)
Bo Zong (NEC Labs)
Wei Cheng (NEC Laboratories America)
Wei Cheng

Wei Cheng is a Senior Researcher at NEC Labs America. He received his Ph.D. from the Department of Computer Science, UNC at Chapel Hill in 2015, advised by Prof. Wei Wang. His research interests include data science, machine learning and bioinformatics. He has filed more than sixty patents, and has published more than 100 research papers in top-tier conferences such as NeurIPS, ICML, SIGKDD, ICLR, WWW, EMNLP, ISMB and journals such as Nature, Science, TNNLS, TKDE, Bioinformatics, etc. His research results received Best Research Paper Runner-Up Award at SIGKDD 2016 and were nominated for the Best Paper Award at ICDM 2018, ICDM 2017, ICDM 2015 and SDM 2012. He has also served as area chair, senior program committee member for several top-tier conferences including SIGKDD, IJCAI, SDM, AAAI, WSDM, etc.

Dongjin Song (University of Connecticut)
Jingchao Ni (NEC Laboratories America, Inc.)
Wenchao Yu (UCLA)
Haifeng Chen (NEC Labs)
Wei Wang (UCLA)

More from the Same Authors