Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Li, Gaichao"'
Graph pooling methods have been widely used on downsampling graphs, achieving impressive results on multiple graph-level tasks like graph classification and graph generation. An important line called node dropping pooling aims at exploiting learnable
Externí odkaz:
http://arxiv.org/abs/2310.20250
The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a two-step aggre
Externí odkaz:
http://arxiv.org/abs/2310.11025
Graph Transformers, emerging as a new architecture for graph representation learning, suffer from the quadratic complexity on the number of nodes when handling large graphs. To this end, we propose a Neighborhood Aggregation Graph Transformer (NAGpho
Externí odkaz:
http://arxiv.org/abs/2305.12677
By incorporating the graph structural information into Transformers, graph Transformers have exhibited promising performance for graph representation learning in recent years. Existing graph Transformers leverage specific strategies, such as Laplacia
Externí odkaz:
http://arxiv.org/abs/2211.07970
The graph Transformer emerges as a new architecture and has shown superior performance on various graph mining tasks. In this work, we observe that existing graph Transformers treat nodes as independent tokens and construct a single long sequence com
Externí odkaz:
http://arxiv.org/abs/2206.04910