Learning complex dynamics from data often leads to unstable or unphysical predictions. Here, the authors introduce Dynami-CAL GraphNet, a physics-informed architecture that conserves linear and angula...

Since its 2009 genesis block, the Bitcoin network has processed >1.08 billion (B) transactions representing >8.72B BTC, offering rich potential for machine learning (ML); yet, its pseudonymity and obs...

Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has...

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...

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

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

Learning representations of temporally evolving graphs, also known as Continuous-Time Dynamic Graphs (CTDGs), has gained considerable attention due to their ability to model a wide range of...

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...

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...

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 ...

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...

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 authors introduce CausalBench, a benchmark suite that enhances network inference evaluation with real-world, large-scale single-cell perturbation data.

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...

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...

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...

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...

Thank you for your interest in reviewing research submissions for the Temporal Graph Learning Workshop@ KDD 2025. Please fill out the information in this form, so we can know more about your backgroun...

Key dates

Catheter ablation of Atrial Fibrillation (AF) consists of a one-size-fits-all treatment with limited success in persistent AF. This may be due to our inability to map the dynamics of AF with the limit...

Homophily principle, \ie{} nodes with the same labels or similar attributes are more likely to be connected, has been commonly believed to be the main reason for the superiority of Graph Neural Networ...

Node centralities play a pivotal role in network science, social network analysis, and recommender systems. In temporal data, static path-based centralities like closeness or betweenness can give...

Many real world graphs are inherently dynamic, constantly evolving with node and edge additions. These graphs can be represented by temporal graphs, either through a stream of edge events or a...

Many real world graphs are inherently dynamic, constantly evolving with node and edge additions. These graphs can be represented by temporal graphs, either through a stream of edge events or a...