Page 197 - 《软件学报》2025年第9期

4108 软件学报 2025 年第 36 卷第 9 期

[30] Haghighatlari M, Li J, Guan XY, Zhang OF, Das A, Stein CJ, Heidar-Zadeh F, Liu ML, Head-Gordon M, Bertels L, Hao HX, Leven I,
Head-Gordon T. NewtonNet: A Newtonian message passing network for deep learning of interatomic potentials and forces. Digital
Discovery, 2022, 1(3): 333–343. [doi: 10.1039/d2dd00008c]
[31] Batzner S, Musaelian A, Sun LX, Geiger M, Mailoa JP, Kornbluth M, Molinari N, Smidt TE, Kozinsky B. E(3)-equivariant graph neural
networks for data-efficient and accurate interatomic potentials. Nature Communications, 2022, 13(1): 2453. [doi: 10.1038/s41467-022-
29939-5]
[32] Gasteiger J, Giri S, Margraf JT, Günnemann S. Fast and uncertainty-aware directional message passing for non-equilibrium molecules. In:
Proc. of the 2020 Machine Learning for Molecules Workshop. NeurIPS, 2020. 1–6.
[33] Gasteiger J, Groß J, Günnemann S. Directional message passing for molecular graphs. In: Proc. of the 2020 Int’l Conf. on Learning
Representations (ICLR). OpenReview.net, 2020.
[34] Unke OT, Chmiela S, Gastegger M, Schütt KT, Sauceda HE, Müller KR. SpookyNet: Learning force fields with electronic degrees of
freedom and nonlocal effects. Nature Communications, 2021, 12(1): 7273. [doi: 10.1038/s41467-021-27504-0]
[35] Hu SY, Zhang WT, Sha QC, Pan F, Wang LW, Jia WL, Tan GM, Zhao T. RLEKF: An optimizer for deep potential with ab initio
accuracy. In: Proc. of the 2023 AAAI Conf. on Artificial Intelligence. Washington DC: AAAI, 2023. 7910–7918. [doi: 10.1609/aaai.
v37i7.25957]
[36] Huang YF, Kang J, Goddard III WA, Wang LW. Density functional theory based neural network force fields from energy
decompositions. Physical Review B, 2019, 99(6): 064103. [doi: 10.1103/PhysRevB.99.064103]
[37] Novikov IS, Gubaev K, Podryabinkin EV, Shapeev AV. The MLIP package: Moment tensor potentials with MPI and active learning.
Machine Learning: Science and Technology, 2021, 2(2): 025002. [doi: 10.1088/2632-2153/abc9fe]
[38] Drautz R. Atomic cluster expansion for accurate and transferable interatomic potentials. Physical Review B, 2019, 99(1): 014104. [doi: 10.
1103/PhysRevB.99.014104]
[39] Lysogorskiy Y, van der Oord C, Bochkarev A, Menon S, Rinaldi M, Hammerschmidt T, Mrovec M, Thompson A, Csányi G, Ortner C,
Drautz R. Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon. npj Computational
Materials, 2021, 7(1): 97. [doi: 10.1038/s41524-021-00559-9]
[40] Bartók AP, Kondor R, Csányi G. On representing chemical environments. Physical Review B, 2013, 87(18): 184115. [doi: 10.1103/
physrevb.87.184115]
[41] Kingma DP, Ba LJ. Adam: A method for stochastic optimization. In: Proc. of the 2015 Int’l Conf. on Learning Representations. Ithaca,
2015.
[42] Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. The Journal of Machine
Learning Research, 2011, 12: 2121–2159.
[43] McMahan HB, Streeter M. Adaptive bound optimization for online convex optimization. In: Proc. of the 23rd Annual Conf. on Learning
Theory. 2010. 244–256.
[44] Kurbiel T, Khaleghian S. Training of deep neural networks based on distance measures using RMSProp. arXiv:1708.01911, 2017.
[45] Zeiler MD. ADADELTA: An adaptive learning rate method. arXiv:1212.5701, 2012.
[46] Martens J, Grosse R. Optimizing neural networks with Kronecker-factored approximate curvature. In: Proc. of the 32nd Int’l
Conf. on Int’l Conf. on Machine Learning. Lille: JMLR.org, 2015. 2408–2417.
[47] Liu DC, Nocedal J. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 1989, 45(1–3):
503–528. [doi: 10.1007/bf01589116]
[48] Zhu CY, Byrd RH, Lu PH, Nocedal J. Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound constrained optimization.
ACM Trans. on Mathematical Software (TOMS), 1997, 23(4): 550–560. [doi: 10.1145/279232.279236]
[49] Gupta V, Koren T, Singer Y. Shampoo: Preconditioned stochastic tensor optimization. In: Proc. of the 35th Int’l Conf. on Machine
Learning. Stockholm: PMLR, 2018. 1842–1850.
[50] Yao ZW, Gholami A, Shen S, Mustafa M, Keutzer K, Mahoney M. ADAHESSIAN: An adaptive second order optimizer for machine
learning. In: Proc. of the 2021 AAAI Conf. on Artificial Intelligence. Palo Alto: AIAA, 2021. 10665–10673. [doi: 10.1609/aaai.v35i12.
17275]
[51] Kalman RE. A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 1960, 82(1): 35–45. [doi: 10.1115/
1.3662552]
[52] Witkoskie JB, Doren DJ. Neural network models of potential energy surfaces: Prototypical examples. Journal of Chemical Theory and
Computation, 2005, 1(1): 14–23. [doi: 10.1021/ct049976i]
[53] Haykin S. Kalman Filtering and Neural Networks. Wiley Online Library, 2001. [doi: 10.1002/0471221546]