Litcius/Paper detail

AdaGCL

Yili Wang, Kaixiong Zhou, Rui Miao, Ninghao Liu, Xin Wang

2022Proceedings of the 31st ACM International Conference on Information & Knowledge Management13 citationsDOI

Abstract

Training graph neural networks (GNNs) with good generalizability on large-scale graphs is a challenging problem. Existing methods mainly divide the input graph into multiple subgraphs and train them in different batches to improve training scalability. However, the local batches obtained by such a strategy could contain topological bias compared with the complete graph structure. It has been studied that the topological bias results in more significant gaps between training and testing performances, or worse generalization robustness. A straightforward solution is to utilize contrastive learning, and train node embeddings to be robust and invariant among the augmented imperfect graphs. However, most of the existing work are inefficient by contrasting extensive node pairs at the large-scale graph. With random data augmentation, they may deteriorate the embedding process by transforming well-sampled batches into meaningless graph structures.

Topics & Concepts

Computer scienceAdvanced Graph Neural NetworksMultimodal Machine Learning ApplicationsAdvanced Image and Video Retrieval Techniques
AdaGCL | Litcius