arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.15015cs.LG
收藏

迈向开放时序图神经网络

Towards Open Temporal Graph Neural Networks

Beijing Institute of Technology(北京理工大学);Ant Group(蚂蚁集团)

Kaituo Feng, Changsheng Li, Xiaolu Zhang, Jun Zhou

AI总结:

本文提出OTGNet,通过解耦节点知识并基于信息瓶颈原理只在不同类节点间传播类别无关信息,同时选择重要多样的三元组子图结构,以解决开放时序图中的动态信息传播和旧类灾难性遗忘问题。

摘要:

近年来,针对时序图的图神经网络(GNN)受到越来越多的关注,其中一个常见假设是节点的类别集合是封闭的。然而,在现实场景中,随着时间推移,类别集合会动态增加,因此常常面临开放集问题。这将给现有的动态GNN方法带来两大挑战:(i)如何在开放时序图中动态传播合适的信息,其中新类别的节点往往与旧类别的节点相连。这种情况会导致尖锐的矛盾。这是因为典型的GNN倾向于使相连节点的嵌入变得相似,而我们期望这两个交互节点的嵌入是可区分的,因为它们属于不同的类别。(ii)在学习时序图中出现的新类别时,如何避免对旧类别的灾难性知识遗忘。在本文中,我们针对开放时序图提出了一种通用且有原则的学习方法,称为OTGNet,目标是解决上述两个挑战。我们假设节点的知识可以被解耦为类别相关知识和类别无关知识,并由此探索一种新的消息传递机制,通过扩展信息瓶颈原理,仅在不同类别节点之间传播类别无关知识,避免聚合冲突信息。此外,我们设计了一种策略来选择既重要又多样的三元组子图结构,以实现有效的类别增量学习。在三个不同领域的真实世界数据集上的大量实验表明,与基线方法相比,我们的方法具有优越性。

英文摘要:

Graph neural networks (GNNs) for temporal graphs have recently attracted increasing attentions, where a common assumption is that the class set for nodes is closed. However, in real-world scenarios, it often faces the open set problem with the dynamically increased class set as the time passes by. This will bring two big challenges to the existing dynamic GNN methods: (i) How to dynamically propagate appropriate information in an open temporal graph, where new class nodes are often linked to old class nodes. This case will lead to a sharp contradiction. This is because typical GNNs are prone to make the embeddings of connected nodes become similar, while we expect the embeddings of these two interactive nodes to be distinguishable since they belong to different classes. (ii) How to avoid catastrophic knowledge forgetting over old classes when learning new classes occurred in temporal graphs. In this paper, we propose a general and principled learning approach for open temporal graphs, called OTGNet, with the goal of addressing the above two challenges. We assume the knowledge of a node can be disentangled into class-relevant and class-agnostic one, and thus explore a new message passing mechanism by extending the information bottleneck principle to only propagate class-agnostic knowledge between nodes of different classes, avoiding aggregating conflictive information. Moreover, we devise a strategy to select both important and diverse triad sub-graph structures for effective class-incremental learning. Extensive experiments on three real-world datasets of different domains demonstrate the superiority of our method, compared to the baselines.

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。

↑