2026-07-10 04:00 UTCOriginal source2 min readUpdated: 2026-07-10 08:11 UTC

Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution

This paper introduces MemExplainer, a method that explains Temporal Graph Network (TGN) predictions using a topology attribution tree and a memory backtracking tree. It accounts for the memory module, quantifies the influence of historical events on node memory vectors, and ensures the sum of event contributions equals model logits via Layer-wise Relevance Propagation (LRP). Experiments on nine datasets covering node property prediction, link prediction, and graph classification show faithful explanations outperforming state-of-the-art baselines. The paper is a Spotlight at ICML 2026.

SourcearXiv Machine LearningAuthor: Yazheng Liu, Xi Zhang, Sihong Xie, Hui Xiong

Article intelligence

EngineersAdvanced

Key points

Existing TGN explanation methods overlook the memory module; this work is the first to incorporate it into the explanation framework.
Proposes topology attribution tree and memory backtracking tree to capture neighbor influence and historical event contributions.
Applies LRP to ensure total event contribution equals model logits, and designs optimization objectives to address top-k unfaithfulness.
Experiments on nine temporal graph datasets across multiple tasks outperform state-of-the-art baselines.

Why it matters

This matters because existing TGN explanation methods overlook the memory module; this work is the first to incorporate it into the explanation framework.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

This panel is AI-generated and reviewed for accuracy.

-->

[Submitted on 4 Jul 2026]

Title:Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution

View a PDF of the paper titled Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution, by Yazheng Liu and 3 other authors

View PDF HTML (experimental)

Abstract:Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy. Understanding which historical events drive model predictions can enhance trustworthiness of TGNs. Existing explanation methods overlook the memory module, the core component that records and updates node histories, leaving the influence of past events unexplored. To address this, we attribute TGNs predictions through the topology attribution tree and memory backtracking tree. The topology attribution tree captures the influence of neighbors and their memory vectors, then the memory backtracking tree quantifies how historical events shape node memory vectors. We apply the LRP in TGNs, ensuring that the total contribution of events equals the logits of model. Finally, top-k selection may be unfaithful due to the nonlinear mapping from logits to probabilities, we design optimization objectives to identify the important events. Experiments on nine temporal graph datasets, spanning node property prediction, link prediction tasks and graph classification tasks, show that our method provides faithful explanations and outperforms state-of-the-art baselines. The code is available at this https URL

Comments: ICML 2026 Spotlight

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.07716 [cs.LG]

(or arXiv:2607.07716v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.07716

arXiv-issued DOI via DataCite

Submission history

From: Yazheng Liu [view email] [v1] Sat, 4 Jul 2026 08:35:07 UTC (4,799 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution, by Yazheng Liu and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-07

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)