Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning. Interestingly, we found that although both RNN and SAM could lead to a good performance, in practice neither of them is always necessary. In this paper, we propose GraphMixer, a conceptually and technically simple architecture that consists of three components: (1) a link-encoder that is only based on multi-layer perceptrons (MLP) to summarize the information from temporal links, (2) a node-encoder that is only based on neighbor mean-pooling to summarize node information, and (3) an MLP-based link classifier that performs link prediction based on the outputs of the encoders. Despite its simplicity, GraphMixer attains an outstanding performance on temporal link prediction benchmarks with faster convergence and better generalization performance. These results motivate us to rethink the importance of simpler model architecture.

翻译：循环神经网络（RNN）和自注意力机制（SAM）是时序图学习中提取时空信息的常用方法。有趣的是，我们发现尽管RNN和SAM都能带来良好的性能，但在实际应用中它们并非总是必需的。本文提出了GraphMixer，一个概念和技术上都十分简洁的架构，包含三个组成部分：（1）仅基于多层感知机（MLP）的链接编码器，用于总结时序链接信息；（2）仅基于邻居均值池化的节点编码器，用于总结节点信息；（3）基于MLP的链接分类器，根据编码器输出进行链接预测。尽管简单，GraphMixer在时序链接预测基准测试中取得了卓越的表现，具有更快的收敛速度和更好的泛化性能。这些结果促使我们重新思考简单模型架构的重要性。