English
Related papers

Related papers: Ensemble Knowledge Distillation for Machine Learni…

200 papers

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student. Existing methods focus on excavating the knowledge hints and transferring the whole knowledge to the student. However,…

Computer Vision and Pattern Recognition · Computer Science 2022-07-13 Chenxin Li , Mingbao Lin , Zhiyuan Ding , Nie Lin , Yihong Zhuang , Yue Huang , Xinghao Ding , Liujuan Cao

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature…

Computer Vision and Pattern Recognition · Computer Science 2023-05-12 Aman Shrivastava , Yanjun Qi , Vicente Ordonez

Machine Learning Interatomic Potentials (MLIPs) achieve near ab initio accuracy at a fraction of the cost of quantum-mechanical simulations, yet they remain prone to silent failures on out-of-distribution configurations, making principled…

Computational Engineering, Finance, and Science · Computer Science 2026-05-27 Olga Zaghen , Maksim Zhdanov , Dario Coscia , David R. Wessels , Erik J. Bekkers

Training machine learning interatomic potentials (MLIPs) on total energies of molecular clusters using differential or transfer learning is becoming a popular route to extend the accuracy of correlated wave-function theory to condensed…

Chemical Physics · Physics 2025-09-23 Mikołaj J. Gawkowski , Mingjia Li , Benjamin X. Shi , Venkat Kapil

Machine learning interatomic potentials (MLIPs) based on a large dataset obtained by density functional theory (DFT) calculation have been developed recently. This study gives both conceptual and practical bases for the high accuracy of…

Materials Science · Physics 2017-11-08 Akira Takahashi , Atsuto Seko , Isao Tanaka

Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data…

Machine Learning · Computer Science 2025-06-23 Naoki Matsumura , Yuta Yoshimoto , Yuto Iwasaki , Meguru Yamazaki , Yasufumi Sakai

The quantization of deep neural networks (QDNNs) has been actively studied for deployment in edge devices. Recent studies employ the knowledge distillation (KD) method to improve the performance of quantized networks. In this study, we…

Machine Learning · Computer Science 2020-10-01 Yoonho Boo , Sungho Shin , Jungwook Choi , Wonyong Sung

In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Qi Zhao , Shuchang Lyu , Zhiwei Zhang , Ting-Bing Xu , Guangliang Cheng

Multi-teacher knowledge distillation (KD), a more effective technique than traditional single-teacher methods, transfers knowledge from expert teachers to a compact student model using logit or feature matching. However, most existing…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Amir M. Mansourian , Amir Mohammad Babaei , Shohreh Kasaei

Off-policy ensemble reinforcement learning (RL) methods have demonstrated impressive results across a range of RL benchmark tasks. Recent works suggest that directly imitating experts' policies in a supervised manner before or during the…

Machine Learning · Computer Science 2020-02-04 Zhang-Wei Hong , Prabhat Nagarajan , Guilherme Maeda

Knowledge Distillation (KD) has emerged as a promising approach for transferring knowledge from a larger, more complex teacher model to a smaller student model. Traditionally, KD involves training the student to mimic the teacher's output…

Machine Learning · Computer Science 2024-10-03 Noel Loo , Fotis Iliopoulos , Wei Hu , Erik Vee

Machine learning interatomic potentials (MLIPs) have become powerful tools to extend molecular simulations beyond the limits of quantum methods, offering near-quantum accuracy at much lower computational cost. Yet, developing reliable MLIPs…

Materials Science · Physics 2025-12-30 Adam Lahouari , Jutta Rogal , Mark E. Tuckerman

This letter presents a novel approach for identifying uncorrelated atomic configurations from extensive data sets with a non-standard neural network workflow known as random network distillation (RND) for training machine-learned…

Computational Physics · Physics 2023-09-08 Jan Finkbeiner , Samuel Tovey , Christian Holm

Machine-learning (ML) interatomic potentials (IPs) trained on first-principles datasets are becoming increasingly popular since they promise to treat larger system sizes and longer time scales, compared to the {\em ab initio} techniques…

Materials Science · Physics 2023-09-04 Shuaihua Lu , Luca M. Ghiringhelli , Christian Carbogno , Jinlan Wang , Matthias Scheffler

Sequential recommendation aims to capture users' dynamic interest and predicts the next item of users' preference. Most sequential recommendation methods use a deep neural network as sequence encoder to generate user and item…

Information Retrieval · Computer Science 2023-05-17 Hanwen Du , Huanhuan Yuan , Pengpeng Zhao , Fuzhen Zhuang , Guanfeng Liu , Lei Zhao , Victor S. Sheng

We present an active learning framework for efficiently generating training data for machine-learned interatomic potentials (MLIPs). The method combines local entropy-driven molecular dynamics with global dataset-aware filtering: a…

Materials Science · Physics 2026-05-21 Meiyan Wang , Rishi Rao , Li Zhu

Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student…

Machine Learning · Computer Science 2022-10-13 Chaofei Wang , Qisen Yang , Rui Huang , Shiji Song , Gao Huang

Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD methods treat all samples uniformly, overlooking the varying…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Chi-Ping Su , Ching-Hsun Tseng , Bin Pu , Lei Zhao , Jiewen Yang , Zhuangzhuang Chen , Shin-Jye Lee

We introduce a lightweight universal machine-learning interatomic potential (uMLIP), SevenNet-Nano, based on the graph neural network architecture SevenNet and enabled by a knowledge-distillation framework. The model inherits the broad…

Materials Science · Physics 2026-04-14 Sangmin Oh , Jinmu You , Jaesun Kim , Jiho Lee , Hyungmin An , Seungwu Han , Youngho Kang

Machine learning interatomic potentials (MLIPs) offer near-ab initio accuracy with the efficiency of classical force fields, making them attractive for modeling electrolytes. Collecting a diverse training set is essential for their accuracy…

Chemical Physics · Physics 2025-10-07 Olga Chalykh , Mikhail Polovinkin , Dmitry Korogod , Nikita Rybin , Alexander Shapeev