Temporal Graph Learning Reading Group

Bridging Theory and Practice in Link Representation with Graph Neural Networks Graph Neural Networks (GNNs) are widely used to compute representations of node pairs for downstream tasks such as link prediction. Yet, theoretical understanding of their expressive power has focused...

arxiv.org/abs/2506.24018

zoom link on website

⏰Time-zone info: Canada already switched to EDT, Europe is still on winter time. See you Thu, Mar 12th, 11amEDT/4pmCET.

We’re happy to welcome Veronica Lachi with “Bridging Theory and Practice in Link Representation with Graph Neural Networks” (NeurIPS 2025)

GitHub - snap-stanford/plurel: PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models - snap-stanford/plurel

Code: github.com/snap-stanfor...

Website: snap-stanford.github.io/plurel/

📚 Today at the Reading Group, Thu, Feb 26, 11am EST, we’re excited to host Vignesh Kothapalli (Stanford University) presenting:

PLUREL: Synthetic Data Unlocks Scaling Laws for Relational Foundation Models

zoom link on our website
See you there! 🚀

link to the paper: openreview.net/forum?id=jdK...

This week at the reading group, thursday feb 12th, 11am EST, we are happy to welcome Sofiane Ennadir, who will present: Virtual Nodes Go Temporal (LOG 2025).

zoom link on website!
🥳

The Temporal Graph Learning Reading Group is back from Winter Break ❄️

See you on Feb 5th, 11am EST

Ivan Marisca will present: Over-squashing in Spatiotemporal Graph Neural Networks (NeurIPS 2025)

more info on our website

📣 Join us for the TENET satellite at @netsciconf.bsky.social in Boston!
Following the enthusiasm for last year’s editions, we're bringing together researchers working on Temporal Networks!
✏️2 pages abstracts
📆 Submit by Feb 20, 2026
🔗 more info here: tinyurl.com/4zevnyft

TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networ...

paper link: arxiv.org/abs/2510.07586

📢 This week at the Reading Group (Nov 13, 11am EST / 5pm CET), Jacob Chmura & @shenyanghuangtg.bsky.social
present TGM: a Modular and Efficient Library for Machine Learning on Temporal Graph ⏰

zoom link on website!

find the paper here: arxiv.org/pdf/2503.02859

🪩This week at the reading group, thursday, november 6th, 11am EST (5pm CET), Emma Ceccherini (University of Bristol) will present: Unsupervised Attributed Dynamic Network Embedding with Stability Guarantees 🪩

Looking forward to seeing you!
zoom link on website.

Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy Machine Learning Decentralized machine learning - where each client keeps its own data locally and uses its own computational resources to collaboratively train a model by exchanging peer-to-peer messages - is increas...

🗓️ Reading Group: Thu, Oct 30 @ 11:00 AM EDT (note: 4:00 PM CET this week due to DST shift!)
👩‍🔬 Speaker: Edwige Cyffers (ISTA, Austria)
📄 Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy ML
🔗 arxiv.org/abs/2505.20882

zoom link on website :)

Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, existing GSSMs operate ...

paper: arxiv.org/abs/2505.18728

This week at the reading group, thursday, Oct 23rd, 11am EDT, we are happy to have Andrea Ceni (University of Pisa), who will present "Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling".

zoom link on website. 🥳

paper link: www.esann.org/sites/defaul...

This week at the reading group, thursday, oct 16th, 11am EDT, we are very happy to welcome @manueldileo.bsky.social who will present Tensor Decomposition for Temporal Knowledge Graph Reasoning: From Completion to Forecasting.

See you there 🥳🥳
zoom link on our website

Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as tempo...

arxiv.org/abs/2509.00975

This week at the reading group, thursday, Oct 9th, 11am EDT (5pm CEST), @Zifeng Ding will present:
Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning 😊

zoom link on website!

The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics In recent years, the expressive power of various neural architectures -- including graph neural networks (GNNs), transformers, and recurrent neural networks -- has been characterised using tools from ...

📚 The TGL reading group is hosting another session tomorrow 📚!

We're excited to have Lu Yi from Renmin University of China on to discuss the paper "Future Link Prediction Without Memory or Aggregation"!

🔗 Paper | arxiv.org/abs/2505.19408
Zoom link can be found on the website - hope to see you!

A large-scale benchmark for network inference from single-cell perturbation data - Communications Biology The authors introduce CausalBench, a benchmark suite that enhances network inference evaluation with real-world, large-scale single-cell perturbation data.

This thursday, Sept 11th, 11am EDT (5pm CEST) we are happy to have Mathieu Chevalley (ETH Zurich and GSK), who will present:
A large-scale benchmark for network inference from single-cell perturbation data

www.nature.com/articles/s42...

zoom link on website 🥳

MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs Temporal Graph Learning (TGL) has become a robust framework for discovering patterns in dynamic networks and predicting future interactions. While existing research has largely concentrated on learnin...

📚 This week, another reading group:
🗓️ Thursday, August 28th | 🕚 11am EDT, 5pm CEST
🎤 Kiarash Shamsi, University of Manitoba presents MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs
🔗 Paper | arxiv.org/abs/2406.10426
👩‍💻: Zoom link on the webpage!

Are Large Language Models Good Temporal Graph Learners? Large Language Models (LLMs) have recently driven significant advancements in Natural Language Processing and various other applications. While a broad range of literature has explored the graph-reaso...

This week at the reading group, thursday, August 14th, 11am EDT (5pm CEST), @shenyanghuangtg.bsky.social will present: Are Large Language Models Good Temporal Graph Learners?

paper: arxiv.org/abs/2506.05393

zoom link on website

looking forward to seeing you! 🥳

escholarship.org/content/qt46...

Good news: The reading group starts again this thursday, july 24th, 11am EDT!

We are happy to welcome Zijie Huang (Google DeepMind) to present:
Neural Dynamics for Science: The Symbiosis of Deep Graph Learning and Differential Equations

Meet you on zoom (link on website) 🎉🥳

💡deadline extension for our Temporal Graph Learning workshop: new deadline is May 25th, AOE 💡

looking forward to your submissions!

Submission deadline for our #kdd2025
workshop is in 6 days, on May 20th AOE.😌

Topics include: Frontiers, Applications, Theory, Models, Methods and Evaluation for learning on temporal graphs!

Position papers, extended abstracts and standard papers.

The venue is non-archival.

📚 This week's reading group:
🗓 Thursday, May 1st | 🕚 11am EDT
🎙 Jason Schoeters (Univ. of Florence, DISIA Lab) presents:
Spanners in Temporal Graphs
🔗 Paper | www.sciencedirect.com/science/arti...
🪩zoom link on website.

#Graph #TemporalGraph

TGB-Seq Benchmark: Challenging Temporal GNNs with Complex... Future link prediction is a fundamental challenge in various real-world dynamic systems. To address this, numerous temporal graph neural networks (temporal GNNs) and benchmark datasets have been...

This week at the Reading Group, Lu Yi from ALGO Lab will present: TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics (#ICLR 2025).

See you on thursday, april 24th, 11am EDT 🌟
zoom link on website!

openreview.net/forum?id=8e2...

Temporal Heterogeneous Graph Generation with Privacy, Utility, and... Nowadays, temporal heterogeneous graphs attract much research and industrial attention for building the next-generation Relational Deep Learning models and applications, due to their informative...

☀️This week at the reading group, Thursday, April 17th, 11am EDT, Xinyu He will present:

Temporal Heterogeneous Graph Generation with Privacy, Utility, and Efficiency (ICLR 2025 Spotlight)

Looking forward to seeing you there!
zoom link on website

paper: openreview.net/forum?id=tj5...