From the 1 of 4 linked papers with an AI index.
4 papers
LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph Forecasting
Minwoo Yu, Young-guk Ha
Continuous-time dynamic graph models predict future links by compressing past interactions into neural states. Although effective for forecasting, this computation obscures which e…
Back to All-Entity Ranking: Sampler-Dependent Evaluation in Continuous-Time Dynamic Graphs
Minwoo Yu, Young-guk Ha
The paper shows that using sampled negative destinations in continuous-time dynamic graph next-destination prediction can change model rankings, and proposes evaluating with all-en…
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…
Relevance Is Not Permission: Warranted Attention for Value Contributions
Minwoo Yu, Young-guk Ha
Relevance is not permission. Attention lets a model read key-value items related to the current query, but it does not guarantee that the value contribution of such an item becomes…