Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Explaining Temporal Graph Models through an Explorer-Navigator Framework

Wenwen Xia · Mincai Lai · Caihua Shan · Yao Zhang · Xinnan Dai · Xiang Li · Dongsheng Li

MH1-2-3-4 #32

Keywords: [ graph neural networks ] [ gnn explainers ] [ temporal graphs ] [ Deep Learning and representational learning ]


Abstract:

While GNN explanation has recently received significant attention, existing works are consistently designed for static graphs. Due to the prevalence of temporal graphs, many temporal graph models have been proposed, but explaining their predictions remains to be explored. To bridge the gap, in this paper, we propose T-GNNExplainer for temporal graph model explanation. Specifically, we regard a temporal graph constituted by a sequence of temporal events. Given a target event, our task is to find a subset of previously occurred events that lead to the model's prediction for it. To handle this combinatorial optimization problem, T-GNNExplainer includes an explorer to find the event subsets with Monte Carlo Tree Search (MCTS) and a navigator that learns the correlations between events and helps reduce the search space. In particular, the navigator is trained in advance and then integrated with the explorer to speed up searching and achieve better results. To the best of our knowledge, T-GNNExplainer is the first explainer tailored for temporal graph models. We conduct extensive experiments to evaluate the performance of T-GNNExplainer. Experimental results on both real-world and synthetic datasets demonstrate that T-GNNExplainer can achieve superior performance with up to about 50% improvement in Area under Fidelity-Sparsity Curve.

Chat is not available.