82 citations · 87 across the 5 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Sphere Retraction Normalizations
Jie Zhang, Cheng-Fang Su, Yi-Jui Huang +1
Residual connections are the de facto mechanism for training deep neural networks stably. Geodesic Normalization (GeoNorm) recasts them on a Riemannian manifold, orthogonalizing ea…
cs.LG2021★ 3 cited
MGC: A Complex-Valued Graph Convolutional Network for Directed Graphs
Jie Zhang, Bo Hui, Po-Wei Harn +2
Recent advancements in Graph Neural Networks have led to state-of-the-art performance on graph representation learning. However, the majority of existing works process directed gra…
cs.LG2020★ 82 cited
Ansor: Generating High-Performance Tensor Programs for Deep Learning
Lianmin Zheng, Chengfan Jia, Minmin Sun +9
High-performance tensor programs are crucial to guarantee efficient execution of deep neural networks. However, obtaining performant tensor programs for different operators on vari…