Maho Nakata — accepted AI-conference papers

2025

Tensor Decomposition Networks for Accelerating Machine Learning Force Field Computations

Yuchao Lin, Cong Fu, Zachary Krueger, Haiyang Yu, Maho Nakata, Jianwen Xie +3

NeurIPS 2025poster

SO(3)-equivariant networks are the dominant models for machine learning interatomic potentials (MLIPs). The key operation of such networks is the Clebsch-Gordan (CG) tensor product, which is computationally expensive. To accelerate the computation, we develop tensor decomposition networks (TDNs) as…

Cited by 0 Source ↗code ↗Scholar ↗

2021

OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs

Weihua Hu, Matthias Fey, Hongyu Ren, Maho Nakata, Yuxiao Dong, Jure Leskovec

NeurIPS 2021poster

Enabling effective and efficient machine learning (ML) over large-scale graph data (e.g., graphs with billions of edges) can have a great impact on both industrial and scientific applications. However, existing efforts to advance large-scale graph ML have been largely limited by the lack of a suitab…

Cited by 492 Source ↗code ↗Scholar ↗