Timezone: »
Recently, contrastiveness-based augmentation surges a new climax in the computer vision domain, where some operations, including rotation, crop, and flip, combined with dedicated algorithms, dramatically increase the model generalization and robustness. Following this trend, some pioneering attempts employ the similar idea to graph data. Nevertheless, unlike images, it is much more difficult to design reasonable augmentations without changing the nature of graphs. Although exciting, the current graph contrastive learning does not achieve as promising performance as visual contrastive learning. We conjecture the current performance of graph contrastive learning might be limited by the violation of the label-invariant augmentation assumption. In light of this, we propose a label-invariant augmentation for graph-structured data to address this challenge. Different from the node/edge modification and subgraph extraction, we conduct the augmentation in the representation space and generate the augmented samples in the most difficult direction while keeping the label of augmented data the same as the original samples. In the semi-supervised scenario, we demonstrate our proposed method outperforms the classical graph neural network based methods and recent graph contrastive learning on eight benchmark graph-structured data, followed by several in-depth experiments to further explore the label-invariant augmentation in several aspects.
Author Information
Han Yue (Brandeis University)
Chunhui Zhang (Brandeis University)
Chuxu Zhang (Brandeis University)
Hongfu Liu (Brandeis University)
More from the Same Authors
-
2022 : Graph Contrastive Learning with Cross-view Reconstruction »
Qianlong Wen · Zhongyu Ouyang · Chunhui Zhang · Yiyue Qian · Yanfang Ye · Chuxu Zhang -
2022 : Contrastive Graph Few-Shot Learning »
Chunhui Zhang · Hongfu Liu · Jundong Li · Yanfang Ye · Chuxu Zhang -
2022 : Diving into Unified Data-Model Sparsity for Class-Imbalanced Graph Representation Learning »
Chunhui Zhang · Chao Huang · Yijun Tian · Qianlong Wen · Zhongyu Ouyang · Youhuan Li · Yanfang Ye · Chuxu Zhang -
2022 : NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs »
Yijun Tian · Chuxu Zhang · Zhichun Guo · Xiangliang Zhang · Nitesh Chawla -
2022 Poster: Co-Modality Graph Contrastive Learning for Imbalanced Node Classification »
Yiyue Qian · Chunhui Zhang · Yiming Zhang · Qianlong Wen · Yanfang Ye · Chuxu Zhang -
2021 Poster: Implicit Semantic Response Alignment for Partial Domain Adaptation »
Wenxiao Xiao · Zhengming Ding · Hongfu Liu