We have 6 of 6 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Temporal graph data are recorded in different representations, but whether these differences also determine the scope of learned knowledge reuse remains unclear. This study investigates whether predictive structure learned from relational histories can be reused between continuous-time dynamic graphs (CTDGs) and tempor...
This work proposes trace-guided intervention search, which uses executable reasoning traces as an intermediate representation for intervention synthesis and confirms simulator-level survival for five of six interventions.
A mechanism-constrained predictor is constructed that uses pair recurrence, recency and history position, renewal patterns, and short sequential transitions while learning the compatibility within each mechanism to recover a substantial portion of the performance of strong neural baselines, and the recovered performanc...
Warrant is proposed, which learns how strongly attention-derived item contributions should be transmitted under the current query, and applies learned item-wise permission before aggregation without renormalization, jointly controlling relative allocation and total transmission mass.
Mass-Aware Attention is proposed, which generalizes standard L1 normalization to an Lp family and is positioned as a general normalization principle for improving predictor-facing representation informativeness by controlling repetition invariance in standard attention.
LiFTER turns future-link forecasting into a verifiable grounded computation and achieves competitive historical-negative forecasting and the highest macro explanation ac- curacy and deletion fidelity across four CTDG benchmarks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
