arXiv Machine Learning June 16, 2026 By Derek Regier, Andrew Polyak, Aresh Dadlani, Khosro Salmani

Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2605. 26290v2 Announce Type: replace Abstract: Temporal signed networks (TSNs) model the time evolution of cooperative and adversarial relationships that arise in applications such as social media analysis, trust and reputation systems, and financial transaction networks.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 2

Temporal Motif Signatures for Temporal Graph Neural Networks

arXiv:2606. 01176v1 Announce Type: new Abstract: Real temporal interaction streams carry predictive structure in short-horizon motif patterns -- repetition, reciprocity, star diversity, triadic flow -- that vanilla temporal graph neural networks (TGNNs) often fail to expose to their edge scorers.

By Dylan Sandfelder, Mihai Cucuringu, Xiaowen Dong

arXiv Machine Learning

Jul 28

Predicting Channel Closures in the Lightning Network with Machine Learning

arXiv:2605. 12759v2 Announce Type: replace Abstract: The Lightning Network (LN) is a second-layer protocol for Bitcoin designed to enable fast and cost-efficient off-chain transactions.

By Simone Antonelli, Vincent Davis, Harrison Rush, Anthony Potdevin, Jesse Shrader, Vikash Singh, Emanuele Rossi

benchmarks safety

arXiv Machine Learning

Aug 10

Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning

arXiv:2608. 07158v1 Announce Type: new Abstract: Temporal graph learning has become essential for analyzing real-world systems whose interactions continuously evolve over time, including financial transaction networks, communication systems, and online social platforms.

By Poupak Azad, Cuneyt Gurcan Akcora, Kiarash Shamsi

benchmarks

arXiv Machine Learning

Jun 25

A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction

arXiv:2602. 14239v3 Announce Type: replace-cross Abstract: Predicting links in sparse, continuously evolving networks is a central challenge in network science.

By Nafiseh Sadat Sajadi, Behnam Bahrak, Mahdi Jafari Siavoshani

rag efficiency

arXiv Machine Learning

Jul 31

MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian

arXiv:2209. 00546v5 Announce Type: replace-cross Abstract: Signed and directed networks are ubiquitous in real-world applications.

By Yixuan He, Michael Permultter, Gesine Reinert, Mihai Cucuringu

arXiv Machine Learning

Jul 22

Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs

arXiv:2607. 18412v1 Announce Type: new Abstract: Dynamic graph learning aims to capture evolving structural and semantic patterns in real-world systems, such as fraud detection and recommender systems.

By Huizhe Zhang, Yuchang Zhu, Huazhen Zhong, Liang Chen, Zibin Zheng

rag

Related stories

Temporal Motif Signatures for Temporal Graph Neural Networks

Predicting Channel Closures in the Lightning Network with Machine Learning

Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning

A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction

MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian

Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs