ChebMixer: Efficient Graph Representation Learning with MLP Mixer

arXiv:2403.16358v1 Announce Type: new
Abstract: Graph neural networks have achieved remarkable success in learning graph representations, especially graph Transformer, which has recently shown superior performance on various graph mining tasks. However, graph Transformer generally treats nodes as tokens, which results in quadratic complexity regarding the number of nodes during self-attention computation. The graph MLP Mixer addresses this challenge by using the efficient MLP Mixer technique from computer vision. However, the time-consuming process of extracting graph tokens limits its performance. In …

abstract arxiv attention complexity computation cs.cv graph graph mining graph neural networks graph representation however mining mlp networks neural networks nodes performance representation representation learning results self-attention success tasks tokens transformer type