arXiv Machine Learning June 26, 2026 By Ping Xiong, Thomas Schnake, Klaus-Robert M\"uller, Shinichi Nakajima

Explaining Temporal Graph Neural Networks via Feature-induced Information Flow

Read the original on arXiv Machine Learning →

arXiv:2606. 27201v1 Announce Type: new Abstract: Event-based Temporal Graph Neural Networks (ETGNNs) have demonstrated strong performance across a wide range of applications, including social network analysis, epidemic tracing, recommender systems, and political event forecasting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 28

GTIN: A Unified Framework for Joint Event and Time Prediction in Temporal Graphs

arXiv:2607. 23556v1 Announce Type: cross Abstract: Temporal graphs are increasingly used to model dynamic systems in diverse domains such as social networks, financial networks, and traffic networks.

By Mohammad Ostadmohammadi, Sepehr Kazemi, Hamid R. Rabiee

arXiv AI

Jul 10

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

arXiv:2607. 07716v1 Announce Type: cross Abstract: Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy.

By Yazheng Liu, Xi Zhang, Sihong Xie, Hui Xiong

benchmarks

arXiv Machine Learning

Jun 5

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

arXiv:2606. 05756v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable performance across a range of applications involving graph-structured data, particularly in high-stakes domains.

By Jialiang Yin, Zheng Zhao, Linsey Pang, Bo Dong, Bin Shi, Jiaxing Zhang

benchmarks

arXiv Machine Learning

Aug 27

DeltaGNN: Graph Neural Network with Information Flow Control

DeltaGNN introduces an information flow control mechanism that uses a new connectivity measure, the information flow score, to mitigate over‑smoothing and over‑squashing in Graph Neural Networks. This approach enables linear computational and memory overhead while effectively capturing both short‑range and long‑range node interactions. Experiments on ten diverse real‑world datasets demonstrate superior performance with limited computational complexity.

By Kevin Mancini, Islem Rekik

benchmarks

arXiv Machine Learning

Sep 1

Deep graph kernel point processes over networks

arXiv:2306.11313v5 Announce Type: replace-cross Abstract: Point process models are widely used for continuous-time discrete-event data, where each data point includes time and additional information...

By Zheng Dong, Matthew Repasky, Xiuyuan Cheng, Yao Xie

benchmarks

arXiv AI

Jun 24

Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts

arXiv:2405. 19062v2 Announce Type: replace-cross Abstract: Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems.

By Lanting Fang, Yulian Yang, Yawei Zhang, Shanshan Feng, Kaiyu Feng, Hanning Yuan

One email a morning, machine-written

Related stories

GTIN: A Unified Framework for Joint Event and Time Prediction in Temporal Graphs

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

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability

DeltaGNN: Graph Neural Network with Information Flow Control

Deep graph kernel point processes over networks

Invariant Graph Representations for Continuous-Time Dynamic Graphs Under Distribution Shifts