arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.07032cs.LG
收藏

学习在动态图上进化

Learning to Evolve on Dynamic Graphs

Australian National University(澳大利亚国立大学);Zhejiang University(浙江大学);Westlake University(西湖大学);Westlake Institute for Advanced Study(西湖高等研究院)

Xintao Xiang, Tiancheng Huang, Donglin Wang

摘要:

动态图中的表示学习是一个具有挑战性的问题,因为图的拓扑结构和节点特征在不同的时间是不同的。这就要求模型能够有效地捕捉图的拓扑信息和时态信息。现有的大多数工作都是建立在递归神经网络(RNN)上的,它被用来精确动态图的时间信息,因此它们继承了RNN的相同缺点。在本文中,我们提出了学习进化动态图(LEDG)-一种新的算法,共同学习图形信息和时间信息。具体来说,我们的方法利用基于梯度的元学习来学习更新策略,这些策略在快照上具有比RNN更好的泛化能力。它与模型无关,因此可以在动态图上训练任何基于消息传递的图神经网络(GNN)。为了提高表示能力,我们将嵌入分解为时间嵌入和图的内在嵌入。我们在不同的数据集和下游任务上进行了实验,实验结果验证了我们的方法的有效性。

英文摘要:

Representation learning in dynamic graphs is a challenging problem because the topology of graph and node features vary at different time. This requires the model to be able to effectively capture both graph topology information and temporal information. Most existing works are built on recurrent neural networks (RNNs), which are used to exact temporal information of dynamic graphs, and thus they inherit the same drawbacks of RNNs. In this paper, we propose Learning to Evolve on Dynamic Graphs (LEDG) - a novel algorithm that jointly learns graph information and time information. Specifically, our approach utilizes gradient-based meta-learning to learn updating strategies that have better generalization ability than RNN on snapshots. It is model-agnostic and thus can train any message passing based graph neural network (GNN) on dynamic graphs. To enhance the representation power, we disentangle the embeddings into time embeddings and graph intrinsic embeddings. We conduct experiments on various datasets and down-stream tasks, and the experimental results validate the effectiveness of our method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑