Existing multimodal recommendation models using complex fusion mechanisms (e.g., attention) or multi-stage processes (e.g., early or late fusion) integrate different modalities. However, attention-based adaptive fusion is prone to shortcut learning, where dominant collaborative signals (ID) can overshadow other modalit...
Hang-Tong Xu, Yuanbo Xu, En Wang· Proceedings of the Thirty-Fi...· 0 citations
This work proposes Liquid Gated Attention (LGA), a solver-free parallel temporal operator that introduces a continuous-time inductive bias and formulates hidden state evolution as a fast-weight associative memory, enabling parallel computation across the temporal dimension.
A comprehensive study to investigate the basic characteristics of current Positive-Unlabeled learning methods and proposes a general framework of PU learning by integrating the set-aware empirical risk with pseudo-labeling.
Yuanchao Dai, Zhengzhang Hou, C. Li et al.· Neural Information Processin...· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.