报告题目：Graph Representation Learning
报告地点：ID: 594-434-324 (腾讯会议)
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. 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. Finally, some new research problems in this aspect will be pointed out and over-reviewed.
黄德双，博士，同济大学教授、博士生导师，中国科技大学兼职教授、博士生导师，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。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, H因子73；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。