TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

Rex Ying, Jialin Chen

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repository	Role	Ran
graph-and-geometric-learning/tempme	canonical	2 of 3

Function	Status	Where it lives
eval_one_epoch	Ran	graph-and-geometric-learning/tempme/learn_base.py code served (permissive licence) · get_code("e7f020e7e36c8af2")
norm_imp	Ran	graph-and-geometric-learning/tempme/temp_exp_main.py code served (permissive licence) · get_code("b298368c3b5766bc")
threshold_test	Not yet run	graph-and-geometric-learning/tempme/temp_exp_main.py code served (permissive licence) · get_code("c11b01d7bd8ab4c1")

Repositories linked to this paper

graph-and-geometric-learning/tempme — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Temporal graphs are widely used to model dynamic systems with time-varying interactions. In real-world scenarios, the underlying mechanisms of generating future interactions in dynamic systems are typically governed by a set of recurring substructures within the graph, known as temporal motifs. Despite the success and prevalence of current temporal graph neural networks (TGNN), it remains uncertain which temporal motifs are recognized as the significant indications that trigger a certain prediction from the model, which is a critical challenge for advancing the explainability and trustworthiness of current TGNNs. To address this challenge, we propose a novel approach, called Temporal Motifs Explainer (TempME), which uncovers the most pivotal temporal motifs guiding the prediction of TGNNs. Derived from the information bottleneck principle, TempME extracts the most interaction-related motifs while minimizing the amount of contained information to preserve the sparsity and succinctness of the explanation. Events in the explanations generated by TempME are verified to be more spatiotemporally correlated than those of existing approaches, providing more understandable insights. Extensive experiments validate the superiority of TempME, with up to 8.21% increase in terms of explanation accuracy across six real-world datasets and up to 22.96% increase in boosting the prediction Average Precision of current TGNNs. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.19324")
get_code_for_paper("2310.19324")
have("2310.19324")

Connect an agent — have() is free.