Text-attributed graph (TAG) clustering seeks to identify node groups by jointly exploiting the semantic information encoded in textual attributes and the structural information captured by graph connectivity. Despite significant progress, their performance often becomes less satisfactory under long-tailed distributions...
Yi-Wei Fu, Chun-Chun Chen, Yu-Xing Zhang et al.· Proceedings of the 35th ACM...· 0 citations
To handle zero-inflated and long-tailed cumulative targets, CoGSeq-LTV adopts a zero-inflated mixture log-normal head with MAE-aligned point supervision and validation-calibrated zero-aware inference, and improves over representative LTV baselines across businesses and horizons, including under a later out-of-time eval...
Zi-Yang Su, Yao Zhou, Ke-Lin Liu et al.· 0 citations
DualClusterNet is presented, a causal sequential recommender that composes two population-shared prototype dictionaries that composes two population-shared prototype dictionaries and evaluates on NYC and TKY using a training-only vocabulary and an original-final-target protocol that neither bridges unknown POIs nor sub...
Zi-Yang Su, Guan-Jie Zheng, Ji-Lin Hu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.