Do Temporal Link Predictors Need Learned Memory? A Smoothed-Count Baseline with a Handful of Parameters
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Project page: https://tgb-seq.github.io/leaderboard
Sources
- On the Power of Heuristics in Temporal Graphs
- Are We Really Measuring Progress? Transferring Insights from Evaluating Recommender Systems to Temporal Link Prediction
- Temporal graph models fail to capture global temporal dynamics
- What Do Temporal Graph Learning Models Learn?
- Temporal Graph Benchmark for Machine Learning on Temporal Graphs
- Are Large Language Models Good Temporal Graph Learners?
- Base3: a simple interpolation-based ensemble method for robust dynamic link prediction
- From Link Prediction to Forecasting: Addressing Challenges in Batch-based Temporal Graph Learning
- Improving Temporal Link Prediction via Temporal Walk Matrix Projection
- Temporal Graph Networks for Deep Learning on Dynamic Graphs
- Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
- TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
- Towards Better Dynamic Graph Learning: New Architecture and Unified Library
- Efficient Neural Common Neighbor for Temporal Graph Link Prediction
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks