Chaim Baskin, Moshe Eliasof, Krishna Sri, Ipsit Mantri, Or Feldman
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Node affinity prediction is a common task that is widely used in temporal graph learning with applications in social and financial networks, recommender systems, and more. Recent works have addressed this task by adapting state-of-the-art dynamic link property prediction models to node affinity prediction. However, simple heuristics, such as Persistent Forecast or Moving Average, outperform these models. In this work, we analyze the challenges in training current Temporal Graph Neural Networks for node affinity prediction and suggest appropriate solutions. Combining the solutions, we develop NAVIS -Node Affinity prediction model using Virtual State, by exploiting the equivalence between heuristics and state space models. While promising, training NAVIS is non-trivial. Therefore, we further introduce a dedicated loss function for node affinity prediction. We evaluate NAVIS on TGB and show that it outperforms the state-of-the-art, including heuristics. Our source code is available at https://github.com/orfeld415/NAVIS * Equal contribution. † Work done while interning at the INSIGHT Lab, Ben-Gurion University of the Negev. ‡ Equal supervision.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2510.06940")
get_code_for_paper("2510.06940")
have("2510.06940")
Connect an agent — have() is free.