报告题目：Hierarchical Graph Pooling Method in Graph Neural Networks

演讲摘要：Graph Neural Networks (GNN) have achieved advanced performance in many fields such as traffic prediction, recommendation systems, and computer vision. Recently there are majorities of methods on GNN focusing on graph convolution, and less work about pooling. Existing graph pooling methods mostly are based on Top-k node selection, in which unselected nodes will be directly discarded, caused the loss of feature information. In that case, we propose a novel graph pooling operator called Hierarchical Graph Pooling with Self- Adaptive Cluster Aggregation (HGP-SACA), which uses a sparse and differentiable method to capture the graph structure. Before using Top-k for cluster selection, the unselected clusters are aggregated by an n-hop, and the merged clusters are used for Top-k selection, so that the merged clusters can contain neighborhood clusters enhancing the function of the unselected cluster. This can enhance the function of the unselected cluster. Through extensive theoretical analysis and experimental verification on multiple datasets, our experimental results show that combining the existing GNN architecture with HGP-SACA can achieve state-of-the-art results on multiple graph classification benchmarks, which proves the effectiveness of our proposed model.Moreover, the selection of Top-k in most graph pooling methods is based on experience, We propose a reinforcement learning method to select the best pooling ratio which is called RL-TOPK. We apply our method to several pooling methods based on Top-k selection. The experimental results show that we can quickly find the best pooling ratio, and the accuracy of the model has been further improved.Besides, we are also interested in dynamic graphs. This kind of graph that changes over time is currently rarely studied. we leave this as future work. And neighborhood aggregation-based GNN also is a main direction in our future work.

讲者简介：黄德双教授，毕业于西安电子科技大学，现为同济大学电子与信息工程学院教授、博士生导师。长期从事神经网络、模式识别与生物信息学方面的研究，在国内外等学术期刊上发表了超过230篇SCI论文；曾荣获教育部和安徽省自然科学一等奖各1项、人工智能学会科技进步一等奖奖1项；担任国家科技创新 2030—新一代人工智能重大项目“面向复杂数据处理的新型神经网络模型研究”项目首席专家；担任期刊IEEE/ACM Transactions on Computational Biology & Bioinformatics等杂志编委。他也是IEEE Fellow，国际模式识别学会(IAPR) Fellow，2000年度中科院“百人计划”入选者，中国计算机学会生物信息学专业委员会副主任委员。