On the diversity of multi-head attention
Sign Up to like & getrecommendations! Published in 2021 at "Neurocomputing"
DOI: 10.1016/j.neucom.2021.04.038
Abstract: Abstract Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions. In this work, we propose two approaches to better exploit such diversity for multi-head attention,… read more here.
Keywords: attention; diversity multi; head; head attention ... See more keywords
Diversity Multi-View Clustering With Subspace and NMF-Based Manifold Learning
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3264837
Abstract: Since the complementarity information among multiple views has been exploited to improve the clustering effect significantly, multi-view clustering has become a hot topic, and many multi-view clustering methods have emerged. Most of them only consider… read more here.
Keywords: diversity multi; manifold learning; multi view; view clustering ... See more keywords