We have 4 of 19 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.
This framework combines Multi-scale Time Encoding, which captures record age using learnable time scales and type-specific projections, with Rotary Time Encoding, which represents signed inter-record intervals through rotary transformations during graph propagation.
Gains in VisKG-LM show that the complete visual-memory interface adds value beyond path textualization alone and support compiled visual memory as an alternative to online graph propagation.
Results show that iterative preference learning benefits both concise entity prediction and explicit reasoning, and also shows that iterative preference learning benefits both concise entity prediction and explicit reasoning.
THGFM is proposed, a web-scale temporal heterogeneous graph fusion model that addresses both limitations within a unified dual-path architecture and directly incorporates relative time into the attention score.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
