Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
This work addresses a limitation in graph Transformers for node classification tasks, offering an incremental improvement for researchers and practitioners in graph machine learning.
The paper tackled the problem of tokenized graph Transformers overlooking valuable node information by proposing GCFormer, which uses a hybrid token generator and contrastive learning to enhance node representations, achieving superior performance in node classification across various datasets compared to existing methods.
While tokenized graph Transformers have demonstrated strong performance in node classification tasks, their reliance on a limited subset of nodes with high similarity scores for constructing token sequences overlooks valuable information from other nodes, hindering their ability to fully harness graph information for learning optimal node representations. To address this limitation, we propose a novel graph Transformer called GCFormer. Unlike previous approaches, GCFormer develops a hybrid token generator to create two types of token sequences, positive and negative, to capture diverse graph information. And a tailored Transformer-based backbone is adopted to learn meaningful node representations from these generated token sequences. Additionally, GCFormer introduces contrastive learning to extract valuable information from both positive and negative token sequences, enhancing the quality of learned node representations. Extensive experimental results across various datasets, including homophily and heterophily graphs, demonstrate the superiority of GCFormer in node classification, when compared to representative graph neural networks (GNNs) and graph Transformers.