English
Related papers

Related papers: Lossless Anti-Distillation Sampling

200 papers

Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs. One of the challenges in GAD is to devise graph…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Rongrong Ma , Guansong Pang , Ling Chen , Anton van den Hengel

Federated Learning has been introduced as a new machine learning paradigm enhancing the use of local devices. At a server level, FL regularly aggregates models learned locally on distributed clients to obtain a more general model. Current…

Machine Learning · Computer Science 2022-07-19 Anastasiia Usmanova , François Portet , Philippe Lalanda , German Vega

Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior…

Machine Learning · Computer Science 2024-12-17 Kuangpu Guo , Yuhe Ding , Jian Liang , Ran He , Zilei Wang , Tieniu Tan

Modern generative models are roughly divided into two main categories: (1) models that can produce high-quality random samples, but cannot estimate the exact density of new data points and (2) those that provide exact density estimation, at…

Machine Learning · Computer Science 2022-06-24 Omri Ben-Dov , Pravir Singh Gupta , Victoria Fernandez Abrevaya , Michael J. Black , Partha Ghosh

Model merging offers an effective way to integrate the capabilities of multiple fine-tuned models. However, the performance degradation of the merged model remains a challenge, particularly when none or few data are available. This paper…

Machine Learning · Computer Science 2025-05-28 Jing Xu , Jiazheng Li , Jingzhao Zhang

Using unlabeled wild data containing both in-distribution (ID) and out-of-distribution (OOD) data to improve the safety and reliability of models has recently received increasing attention. Existing methods either design customized losses…

Machine Learning · Computer Science 2025-05-20 Chuanxing Geng , Qifei Li , Xinrui Wang , Dong Liang , Songcan Chen , Pong C. Yuen

Score distillation sampling (SDS) and its variants have greatly boosted the development of text-to-3D generation, but are vulnerable to geometry collapse and poor textures yet. To solve this issue, we first deeply analyze the SDS and find…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Zike Wu , Pan Zhou , Xuanyu Yi , Xiaoding Yuan , Hanwang Zhang

Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts…

Computation and Language · Computer Science 2026-02-17 Manish Dhakal , Uthman Jinadu , Anjila Budathoki , Rajshekhar Sunderraman , Yi Ding

While Federated Learning (FL) is gaining popularity for training machine learning models in a decentralized fashion, numerous challenges persist, such as asynchronization, computational expenses, data heterogeneity, and gradient and…

Machine Learning · Computer Science 2025-03-13 Chun-Yin Huang , Ruinan Jin , Can Zhao , Daguang Xu , Xiaoxiao Li

Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs). While reverse diffusion sampling often requires adjustments of LDM architecture or feature…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Jeongsol Kim , Geon Yeong Park , Jong Chul Ye

Model distillation enables the transfer of knowledge from large-scale models to compact student models, facilitating deployment in resource-constrained environments. However, conventional distillation approaches often suffer from…

Machine Learning · Computer Science 2025-08-21 Suleyman Olcay Polat , Poli A. Nemkova , Mark V. Albert

With the deployment of Large Language Models (LLMs) in interactive applications, online malicious intent detection has become increasingly critical. However, existing approaches fall short of handling diverse and complex user queries in…

Dataset Distillation aims to synthesize compact datasets that can approximate the training efficacy of large-scale real datasets, offering an efficient solution to the increasing computational demands of modern deep learning. Recently,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Chenru Wang , Yunyi Chen , Zijun Yang , Joey Tianyi Zhou , Chi Zhang

The purpose of model selection algorithms such as All Subsets, Forward Selection and Backward Elimination is to choose a linear model on the basis of the same set of data to which the model will be applied. Typically we have available a…

Statistics Theory · Mathematics 2007-06-13 Bradley Efron , Trevor Hastie , Iain Johnstone , Robert Tibshirani

Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (\textit{e.g.}, only classification…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Xuerui Zhang , Xuehao Wang , Zhan Zhuang , Linglan Zhao , Ziyue Li , Xinmin Zhang , Zhihuan Song , Yu Zhang

While federated learning has shown strong results in optimizing a machine learning model without direct access to the original data, its performance may be hindered by intermittent client availability which slows down the convergence and…

Machine Learning · Computer Science 2022-12-08 Zheng Wang , Xiaoliang Fan , Jianzhong Qi , Haibing Jin , Peizhen Yang , Siqi Shen , Cheng Wang

Detecting whether examples belong to a given in-distribution or are Out-Of-Distribution (OOD) requires identifying features specific to the in-distribution. In the absence of labels, these features can be learned by self-supervised…

Artificial Intelligence · Computer Science 2022-01-19 Nima Rafiee , Rahil Gholamipoorfard , Nikolas Adaloglou , Simon Jaxy , Julius Ramakers , Markus Kollmann

Continual learning (CL) aims to learn new tasks without erasing previous knowledge. However, current CL methods primarily emphasize improving accuracy while often neglecting training efficiency, which consequently restricts their practical…

Machine Learning · Computer Science 2026-01-30 RuiQi Liu , Boyu Diao , Libo Huang , Zijia An , Hangda Liu , Zhulin An , Yongjun Xu

Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently…

Computation and Language · Computer Science 2024-06-17 Hancheol Park , Soyeong Jeong , Sukmin Cho , Jong C. Park

Despite the recent success of deep neural networks, there remains a need for effective methods to enhance domain generalization using vision transformers. In this paper, we propose a novel domain generalization technique called Robust…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Ankur Singh , Senthilnath Jayavelu