English
Related papers

Related papers: Step Out and Seek Around: On Warm-Start Training w…

200 papers

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Jialiang Tang , Shuo Chen , Gang Niu , Masashi Sugiyama , Chen Gong

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Vishaal Udandarao , Nikhil Parthasarathy , Muhammad Ferjad Naeem , Talfan Evans , Samuel Albanie , Federico Tombari , Yongqin Xian , Alessio Tonioni , Olivier J. Hénaff

Continual Pre-Training (CPT) is essential for enabling Language Models (LMs) to integrate new knowledge without erasing old. While classical CPT techniques like data replay have become the standard paradigm, the mechanisms underlying how…

Computation and Language · Computer Science 2026-05-12 Haoyu Wang , Yifan Shang , Zhongxiang Sun , Weijie Yu , Xiao Zhang , Jun Xu

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…

Computation and Language · Computer Science 2021-09-24 Lei Li , Yankai Lin , Shuhuai Ren , Peng Li , Jie Zhou , Xu Sun

In the past years, Knowledge-Based Question Answering (KBQA), which aims to answer natural language questions using facts in a knowledge base, has been well developed. Existing approaches often assume a static knowledge base. However, the…

Computation and Language · Computer Science 2021-01-19 Yongqi Li , Wenjie Li , Liqiang Nie

As an emerging paradigm of federated learning, asynchronous federated learning offers significant speed advantages over traditional synchronous federated learning. Unlike synchronous federated learning, which requires waiting for all…

Machine Learning · Computer Science 2025-04-10 Chaoyi Lu , Yiding Sun , Pengbo Li , Zhichuan Yang

Knowledge distillation aims at transferring knowledge acquired in one model (a teacher) to another model (a student) that is typically smaller. Previous approaches can be expressed as a form of training the student to mimic output…

Computer Vision and Pattern Recognition · Computer Science 2019-05-02 Wonpyo Park , Dongju Kim , Yan Lu , Minsu Cho

Knowledge distillation (KD) is a technique for transferring knowledge from complex teacher models to simpler student models, significantly enhancing model efficiency and accuracy. It has demonstrated substantial advancements in various…

Computation and Language · Computer Science 2025-04-21 Junjie Yang , Junhao Song , Xudong Han , Ziqian Bi , Tianyang Wang , Chia Xin Liang , Xinyuan Song , Yichao Zhang , Qian Niu , Benji Peng , Keyu Chen , Ming Liu

The convergence rate and final performance of common deep learning models have significantly benefited from heuristics such as learning rate schedules, knowledge distillation, skip connections, and normalization layers. In the absence of…

Machine Learning · Computer Science 2018-11-01 Akhilesh Gotmare , Nitish Shirish Keskar , Caiming Xiong , Richard Socher

Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general…

Computation and Language · Computer Science 2025-02-26 Guanlin Liu , Anand Ramachandran , Tanmay Gangwani , Yan Fu , Abhinav Sethy

Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series data analysis. These models capture complex, sequential patterns in time series,…

Machine Learning · Computer Science 2026-01-12 Nilushika Udayangani , Kishor Nandakishor , Marimuthu Palaniswami

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Li Shen , Juhua Liu , Bo Du , Dacheng Tao

Knowledge distillation (KD) is generally considered as a technique for performing model compression and learned-label smoothing. However, in this paper, we study and investigate the KD approach from a new perspective: we study its efficacy…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Nandan Kumar Jha , Rajat Saini , Sparsh Mittal

Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often fix the trade-off between keeping old knowledge (stability)…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Kanghao Chen , Sijia Liu , Ruixuan Wang , Wei-Shi Zheng

Deep learning has shown its efficacy in extracting useful features to solve various computer vision tasks. However, when the structure of the data is complex and noisy, capturing effective information to improve performance is very…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Eun Som Jeon , Rahul Khurana , Aishani Pathak , Pavan Turaga

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…

Computation and Language · Computer Science 2024-07-18 Songming Zhang , Yunlong Liang , Shuaibo Wang , Wenjuan Han , Jian Liu , Jinan Xu , Yufeng Chen

Federated Learning (FL) enables collaborative model training across multiple devices while preserving data privacy. However, it remains susceptible to backdoor attacks, where malicious participants can compromise the global model. Existing…

Cryptography and Security · Computer Science 2025-02-26 Ebtisaam Alharbi , Leandro Soriano Marcolino , Qiang Ni , Antonios Gouglidis

Data augmentation is known to improve the generalization capabilities of neural networks, provided that the set of transformations is chosen with care, a selection often performed manually. Automatic data augmentation aims at automating…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Juliette Marrie , Michael Arbel , Diane Larlus , Julien Mairal

We introduce a machine-learning framework to warm-start fixed-point optimization algorithms. Our architecture consists of a neural network mapping problem parameters to warm starts, followed by a predefined number of fixed-point iterations.…

Optimization and Control · Mathematics 2023-09-15 Rajiv Sambharya , Georgina Hall , Brandon Amos , Bartolomeo Stellato

The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Xinyuan Gao , Songlin Dong , Yuhang He , Qiang Wang , Yihong Gong