Results 121 to 130 of about 6,341,676 (193)

Beyond static snapshots: gated recurrent units and graph attention networks for smarter multi-agent traffic control. [PDF]

Front Artif Intell
Mohita, Singh SD, Subitha D, Kavitha JC.
europepmc   +1 more source

Demystifying Oversmoothing in Attention-Based Graph Neural Networks [PDF]

Oversmoothing in Graph Neural Networks (GNNs) refers to the phenomenon where increasing network depth leads to homogeneous node representations. While previous work has established that Graph Convolutional Networks (GCNs) exponentially lose expressive ...
Wu, Zihui, Wu, Xinyi, Ajorlou, Amir, Jadbabaie, Ali   +3 more
core  

Multi-modal dual attention graph contrastive learning for recommendation

Multi-modal recommender systems, incorporating rich content information (e.g., images and texts) into user behavior modeling, have attracted significant attention recently.
Ma, S, Zeng, Y, Xu, G, Wu, S, Shi, K, Zeng, Yawen, Shi, Kaize, Xu, Guandong, Wu, Shiqing, Ma, Shouxing   +9 more
core   +1 more source

Retraction: Sentiment analysis of classical Chinese literature: An unsupervised deep learning model with BERT and graph attention networks. [PDF]

PLoS One
PLOS One Editors.
europepmc   +1 more source

Knowledge-informed graph attention networks enable defect-free alloy design for laser additive manufacturing. [PDF]

Nat Commun
Fu J, Yu H, Wang C, Wang L, Sun Z, Li J, van der Zwaag S, Raabe D, Xu W.   +8 more
europepmc   +1 more source

Adaptive competitive balance regulation in professional sports leagues via graph attention networks and proximal policy optimization. [PDF]

Sci Rep
Hu X, Lin Y.
europepmc   +1 more source

Geometry-aware graph attention networks to explain single-cell chromatin states and gene expression with SEAGALL. [PDF]

Genome Biol
Malagoli G, Hanel P, Danese A, Wolf G, Colomé-Tatché M.   +4 more
europepmc   +1 more source

Improving personalized recommendations system using graph attention networks driven by perceived complexity and innovation. [PDF]

Sci Rep
Ullah S, Khan A, Khan KU, Amanullah, Chohan RT, Khan MN.   +5 more
europepmc   +1 more source

I‑GAT: Interpretable Graph Attention Networks for Ligand Optimization. [PDF]

ACS Omega
Mathew E, Emmitte KA, Liu J.
europepmc   +1 more source

Dynamic spatiotemporal graph attention networks for cross-regional multi-disease forecasting and intervention optimization. [PDF]

Front Public Health
Liu S, Cao L.
europepmc   +1 more source