Your Temporal Link Predictor Is Blind to Who Is Active: A Missing Factor That Transfers Across Models
cs.LG, cs.SI
Submitted: 2026-10-04
Updated: 2026-10-04
Code: https://github.com/Erutaner/YourTemporal-Link-Predictor-Is-Blind-to-Who-Is-Active
Sources
- Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
- Time2Vec: Learning a Vector Representation of Time
- DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs
- Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks
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