English
Related papers

Related papers: Random Teachers are Good Teachers

200 papers

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

Computation and Language · Computer Science 2025-10-27 Benjamin Minixhofer , Ivan Vulić , Edoardo Maria Ponti

Knowledge distillation between machine learning models has opened many new avenues for parameter count reduction, performance improvements, or amortizing training time when changing architectures between the teacher and student network. In…

Machine Learning · Computer Science 2020-11-24 Jonathan Raiman

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Pengpeng Liu , Michael R. Lyu , Irwin King , Jia Xu

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)…

It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions. In this paper, we present a Linear Distillation Learning, a simple remedy to improve the…

Machine Learning · Computer Science 2019-10-14 Arip Asadulaev , Igor Kuznetsov , Andrey Filchenkov

Recently, the teacher-student knowledge distillation framework has demonstrated its potential in training Graph Neural Networks (GNNs). However, due to the difficulty of training over-parameterized GNN models, one may not easily obtain a…

Machine Learning · Computer Science 2021-05-03 Yuzhao Chen , Yatao Bian , Xi Xiao , Yu Rong , Tingyang Xu , Junzhou Huang

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

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

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Dang Nguyen , Sunil Gupta , Kien Do , Svetha Venkatesh

Dropout is a widely-used regularization technique, often required to obtain state-of-the-art for a number of architectures. This work demonstrates that dropout introduces two distinct but entangled regularization effects: an explicit effect…

Machine Learning · Computer Science 2020-10-16 Colin Wei , Sham Kakade , Tengyu Ma

In gradient descent, changing how we parametrize the model can lead to drastically different optimization trajectories, giving rise to a surprising range of meaningful inductive biases: identifying sparse classifiers or reconstructing…

Machine Learning · Statistics 2021-11-24 Anna Kerekes , Anna Mészáros , Ferenc Huszár

Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Eli Verwimp , Kuo Yang , Sarah Parisot , Hong Lanqing , Steven McDonagh , Eduardo Pérez-Pellitero , Matthias De Lange , Tinne Tuytelaars

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Mobarakol Islam , Lalithkumar Seenivasan , S. P. Sharan , V. K. Viekash , Bhavesh Gupta , Ben Glocker , Hongliang Ren

While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and…

Machine Learning · Computer Science 2015-03-30 Adriana Romero , Nicolas Ballas , Samira Ebrahimi Kahou , Antoine Chassang , Carlo Gatta , Yoshua Bengio

Knowledge distillation (KD) has gained much attention due to its effectiveness in compressing large-scale pre-trained models. In typical KD methods, the small student model is trained to match the soft targets generated by the big teacher…

Machine Learning · Computer Science 2021-09-13 Yitao Liu , Tianxiang Sun , Xipeng Qiu , Xuanjing Huang

Growing efforts to improve knowledge distillation (KD) in large language models (LLMs) replace dense teacher supervision with selective distillation, which uses a subset of token positions, vocabulary classes, or training samples for…

Computation and Language · Computer Science 2026-02-03 Almog Tavor , Itay Ebenspanger , Neil Cnaan , Mor Geva

Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Jinjing Zhu , Songze Li , Lin Wang

Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running requirements in practice use. Whilst being able to create…

Computer Vision and Pattern Recognition · Computer Science 2018-11-20 Xu Lan , Xiatian Zhu , Shaogang Gong

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…

Machine Learning · Computer Science 2025-10-03 Qin Shi , Amber Yijia Zheng , Qifan Song , Raymond A. Yeh

While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing…

Computation and Language · Computer Science 2021-09-20 Meghana Moorthy Bhat , Alessandro Sordoni , Subhabrata Mukherjee