English
Related papers

Related papers: Osmosis Distillation: Model Hijacking with the Few…

200 papers

In this paper, we propose that small models may not need to absorb the cost of pre-training to reap its benefits. Instead, they can capitalize on the astonishing results achieved by modern, enormous models to a surprising degree. We observe…

Machine Learning · Computer Science 2024-05-06 Sean Farhat , Deming Chen

Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where…

Machine Learning · Computer Science 2025-02-06 Daniil Tiapkin , Daniele Calandriello , Johan Ferret , Sarah Perrin , Nino Vieillard , Alexandre Ramé , Mathieu Blondel

Dataset distillation compresses a large dataset into a small synthetic dataset such that learning on the synthetic dataset approximates learning on the original. Training on the distilled dataset can be performed in as little as one step of…

Machine Learning · Computer Science 2025-08-14 Connor Wilhelm , Dan Ventura

We study the problem of dataset distillation - creating a small set of synthetic examples capable of training a good model. In particular, we study the problem of label distillation - creating synthetic labels for a small set of real…

Machine Learning · Computer Science 2020-12-15 Ondrej Bohdal , Yongxin Yang , Timothy Hospedales

Policy Distillation (PD) has become an effective method to improve deep reinforcement learning tasks. The core idea of PD is to distill policy knowledge from a teacher agent to a student agent. However, the teacher-student framework…

Machine Learning · Computer Science 2024-06-11 Xinqiang Yu , Chuanguang Yang , Chengqing Yu , Libo Huang , Zhulin An , Yongjun Xu

Dataset distillation (DD) aims to construct compact synthetic datasets that allow models to achieve comparable performance to full-data training while substantially reducing storage and computation. Despite rapid empirical progress, its…

Machine Learning · Computer Science 2025-12-11 Zhengquan Luo , Zhiqiang Xu

Unsupervised deep learning techniques are widely used to identify anomalous behaviour. The performance of such methods is a product of the amount of training data and the model size. However, the size is often a limiting factor for the…

Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their application. As such, a process known as knowledge distillation is…

Information Retrieval · Computer Science 2024-11-05 Vishakha Suresh Kalal , Andrew Parry , Sean MacAvaney

Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is…

Machine Learning · Computer Science 2020-01-01 Yuxiang Sun , Pooyan Fazli

Federated Distillation (FD) is a novel and promising distributed machine learning paradigm, where knowledge distillation is leveraged to facilitate a more efficient and flexible cross-device knowledge transfer in federated learning. By…

Machine Learning · Computer Science 2024-01-09 Yuhan Tang , Zhiyuan Wu , Bo Gao , Tian Wen , Yuwei Wang , Sheng Sun

Few-shot learning deals with problems such as image classification using very few training examples. Recent vision foundation models show excellent few-shot transfer abilities, but are large and slow at inference. Using knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Erik Landolsi , Fredrik Kahl

Replay-based continual learning (CL) methods assume that models trained on a small subset can also effectively minimize the empirical risk of the complete dataset. These methods maintain a memory buffer that stores a sampled subset of data…

Machine Learning · Computer Science 2025-05-29 Wenyang Liao , Quanziang Wang , Yichen Wu , Renzhen Wang , Deyu Meng

Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access the real in-distribution (ID) data. Its common solution is to use a generator to synthesize fake data and use them as a substitute for…

Machine Learning · Computer Science 2025-07-08 Ziming Hong , Runnan Chen , Zengmao Wang , Bo Han , Bo Du , Tongliang Liu

Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare. Recently, self-supervised representation learning techniques (via contrastive learning…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Sina Mohseni , Arash Vahdat , Jay Yadawa

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…

Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 He Liu , Yikai Wang , Huaping Liu , Fuchun Sun , Anbang Yao

While many deep learning models trained on private datasets have been deployed in various practical tasks, they may pose a privacy leakage risk as attackers could recover informative data or label knowledge from models. In this work, we…

Machine Learning · Computer Science 2026-01-28 Bochao Liu , Shiming Ge , Pengju Wang , Shikun Li , Tongliang Liu

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…

Computer Vision and Pattern Recognition · Computer Science 2019-10-31 Tao Wang , Li Yuan , Xiaopeng Zhang , Jiashi Feng

Abstract Diffusion models have recently gained prominence as a novel category of generative models. Despite their success, these models face a notable drawback in terms of slow sampling speeds, requiring a high number of function…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Sanghwan Kim , Hao Tang , Fisher Yu

While deep models have proved successful in learning rich knowledge from massive well-annotated data, they may pose a privacy leakage risk in practical deployment. It is necessary to find an effective trade-off between high utility and…

Machine Learning · Computer Science 2024-09-05 Shiming Ge , Bochao Liu , Pengju Wang , Yong Li , Dan Zeng