English
Related papers

Related papers: Toward Understanding Privileged Features Distillat…

200 papers

Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SFT) and fail to reach the reinforcement learning (RL)…

Our paper addresses the problem of models struggling to learn diverse features, due to either forgetting previously learned features or failing to learn new ones. To overcome this problem, we introduce Diverse Feature Learning (DFL), a…

Artificial Intelligence · Computer Science 2024-04-01 Sejik Park

Most existing federated learning methods are unable to estimate model/predictive uncertainty since the client models are trained using the standard loss function minimization approach which ignores such uncertainties. In many situations,…

Machine Learning · Computer Science 2023-10-03 Shrey Bhatt , Aishwarya Gupta , Piyush Rai

Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years,…

Machine Learning · Computer Science 2023-04-11 Huancheng Chen , Johnny , Wang , Haris Vikalo

Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 YuXing Lee , Wei Wu

We explore a novel perspective of knowledge distillation (KD) for learning to rank (LTR), and introduce Self-Distilled neural Rankers (SDR), where student rankers are parameterized identically to their teachers. Unlike the existing ranking…

Information Retrieval · Computer Science 2022-04-07 Zhen Qin , Le Yan , Yi Tay , Honglei Zhuang , Xuanhui Wang , Michael Bendersky , Marc Najork

The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Tao Huang , Yuan Zhang , Mingkai Zheng , Shan You , Fei Wang , Chen Qian , Chang Xu

Federated learning provides a privacy-preserving manner to collaboratively train models on data distributed over multiple local clients via the coordination of a global server. In this paper, we focus on label distribution skew in federated…

Machine Learning · Computer Science 2024-09-23 Jianghu Lu , Shikun Li , Kexin Bao , Pengju Wang , Zhenxing Qian , Shiming Ge

Knowledge distillation extracts general knowledge from a pre-trained teacher network and provides guidance to a target student network. Most studies manually tie intermediate features of the teacher and student, and transfer knowledge…

Machine Learning · Computer Science 2021-02-08 Mingi Ji , Byeongho Heo , Sungrae Park

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Cheng Cui , Ruoyu Guo , Yuning Du , Dongliang He , Fu Li , Zewu Wu , Qiwen Liu , Shilei Wen , Jizhou Huang , Xiaoguang Hu , Dianhai Yu , Errui Ding , Yanjun Ma

Multivariate time series forecasting (MTSF) endeavors to predict future observations given historical data, playing a crucial role in time series data management systems. With advancements in large language models (LLMs), recent studies…

Machine Learning · Computer Science 2025-05-07 Chenxi Liu , Hao Miao , Qianxiong Xu , Shaowen Zhou , Cheng Long , Yan Zhao , Ziyue Li , Rui Zhao

Real-world object detection models should be cheap and accurate. Knowledge distillation (KD) can boost the accuracy of a small, cheap detection model by leveraging useful information from a larger teacher model. However, a key challenge is…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Chenhongyi Yang , Mateusz Ochal , Amos Storkey , Elliot J. Crowley

Knowledge distillation is a model compression technique in which a compact "student" network is trained to replicate the predictive behavior of a larger "teacher" network. In logit-based knowledge distillation, it has become the de facto…

Machine Learning · Computer Science 2026-05-12 Ejafa Bassam , Dawei Zhu , Kaigui Bian

Direct Preference Optimization (DPO) is a powerful paradigm to align language models with human preferences using pairwise comparisons. However, its binary win-or-loss supervision often proves insufficient for training small models with…

Computation and Language · Computer Science 2025-09-23 Minchan Kwon , Junwon Ko , Kangil Kim , Junmo Kim

On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal rewards and can yield better generalization than off-policy…

Model-Heterogeneous Federated Learning (Hetero-FL) has attracted growing attention for its ability to aggregate knowledge from heterogeneous models while keeping private data locally. To better aggregate knowledge from clients, ensemble…

Machine Learning · Computer Science 2025-10-15 Yichen Li , Xiuying Wang , Wenchao Xu , Haozhao Wang , Yining Qi , Jiahua Dong , Ruixuan Li

Multimodal recommendation exploits the rich multimodal information associated with users or items to enhance the representation learning for better performance. In these methods, end-to-end feature extractors (e.g., shallow/deep neural…

Information Retrieval · Computer Science 2023-08-08 Fan Liu , Huilin Chen , Zhiyong Cheng , Liqiang Nie , Mohan Kankanhalli

Universal force fields generalizable across the periodic table represent a new trend in computational materials science. However, the applications of universal force fields in material simulations are limited by their slow inference speed…

Materials Science · Physics 2025-12-11 Ruoyu Wang , Yuxiang Gao , Hongyu Wu , Zhicheng Zhong

Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called privileged information, improving the student model, which…

Computation and Language · Computer Science 2024-08-20 Rafael-Edy Menadil , Mariana-Iuliana Georgescu , Radu Tudor Ionescu

In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even displaying emergent properties. However, state-of-the-art methods usually rely on ensembles…

Machine Learning · Computer Science 2026-05-01 Esteban Rodríguez-Betancourt , Edgar Casasola-Murillo