Embargo End Date2021-12-02
Permanent link to this recordhttp://hdl.handle.net/10754/666216
MetadataShow full item record
Access RestrictionsAt the time of archiving, the student author of this thesis opted to temporarily restrict access to it. The full text of this thesis will become available to the public after the expiration of the embargo on 2021-12-02.
AbstractGraph Convolutional Networks (GCNs) draws significant attention due to its power of representation learning on graphs. Recent works developed frameworks to train deep GCNs. Such works show impressive results in tasks like point cloud classification and segmentation, and protein interaction prediction. While for large-scale graphs, doing full-batch training by GCNs is still challenging especially when GCNs go deeper. By fully analyzing a clustering-based mini-batch training algorithm ClusterGCN, we propose random partition which is a more efficient and effective method to implement mini-batch training. Besides, selecting different permutation invariance function (such as max, mean or add) for neighbors’ information aggregation will result in every different results. Therefore, we propose to alleviate it by introducing a novel Generalized Aggregation Function. In this thesis, I analyze the drawbacks caused by ClusterGCN and discuss about its limits. I further compare the performance of ClusterGCN with random partition and the final experimental results show that simple random partition outperforms ClusterGCN with very obvious advantageous for node property prediction task. For the techniques which are commonly used to make GCNs go deeper, I demonstrate a better way of applying residual connections (pre-activation) to stack more layers for GCNs. Last, I show the complete work of training deeper GCNs with generalized aggregators and display the promising results over several datasets from the Open Graph Benchmark (OGB).
CitationXiong, C. (2020). Deep GCNs with Random Partition and Generalized Aggregator. KAUST Research Repository. https://doi.org/10.25781/KAUST-D37F7