6 papers
Learning Across Temporal Graph Representation Silos
Minwoo Yu, Young-guk Ha
Temporal graph data are recorded in different representations, but whether these differences also determine the scope of learned knowledge reuse remains unclear. This study investi…
From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphs
Minwoo Yu, Young-guk Ha
Can a trace explaining model execution also compute the changes needed for a specified alternative prediction? We propose trace-guided intervention search, which uses executable re…
Where Does Neural Advantage Arise in Continuous-Time Dynamic Graph Prediction?
Minwoo Yu, Young-guk Ha
Aggregate performance on continuous-time dynamic graphs (CTDGs) combines, in a single score, the portion attributable to known temporal regularities and the additional predictive p…
Back to All-Entity Ranking: Sampler-Dependent Evaluation in Continuous-Time Dynamic Graphs
Minwoo Yu, Young-guk Ha
Next-destination prediction in continuous-time dynamic graphs (CTDGs) commonly ranks an observed interaction against sampled negative destinations. The resulting score is condition…
What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation
Minwoo Yu, Young-guk Ha
High task performance does not show whether a model retains prediction-relevant structural information in its internal representation. Temporal graph models, for example, can achie…
Warranted Attention: Learning What to Pass from Attention to Prediction
Minwoo Yu, Young-guk Ha
Relevance of information read by attention does not guarantee that its contribution benefits the current prediction. We propose Warrant, which learns how strongly attention-derived…