中文
相关论文

相关论文: On the Surprising Efficacy of Distillation as an A…

200 篇论文

It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to transfer knowledge to the small one via distillation. Despite…

机器学习 · 计算机科学 2021-12-14 Haizhou Shi , Youcai Zhang , Siliang Tang , Wenjie Zhu , Yaqian Li , Yandong Guo , Yueting Zhuang

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets.…

计算机视觉与模式识别 · 计算机科学 2025-05-23 Wenmin Li , Shunsuke Sakai , Tatsuhito Hasegawa

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training. Due to the cost of applying such models to…

计算与语言 · 计算机科学 2019-09-27 Iulia Turc , Ming-Wei Chang , Kenton Lee , Kristina Toutanova

Continual learning requires learning incremental tasks with dynamic data distributions. So far, it has been observed that employing a combination of contrastive loss and distillation loss for training in continual learning yields strong…

机器学习 · 计算机科学 2024-05-30 Yichen Wen , Zhiquan Tan , Kaipeng Zheng , Chuanlong Xie , Weiran Huang

Training effective text rerankers is crucial for information retrieval. Two strategies are widely used: contrastive learning (optimizing directly on ground-truth labels) and knowledge distillation (transferring knowledge from a larger…

计算与语言 · 计算机科学 2025-11-07 Zhichao Xu , Zhiqi Huang , Shengyao Zhuang , Vivek Srikumar

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a…

机器学习 · 计算机科学 2022-01-26 Yonglong Tian , Dilip Krishnan , Phillip Isola

Knowledge distillation is a mainstream algorithm in model compression by transferring knowledge from the larger model (teacher) to the smaller model (student) to improve the performance of student. Despite many efforts, existing methods…

计算机视觉与模式识别 · 计算机科学 2024-10-21 Muhe Ding , Jianlong Wu , Xue Dong , Xiaojie Li , Pengda Qin , Tian Gan , Liqiang Nie

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

计算与语言 · 计算机科学 2023-12-25 Jiahao Xu , Wei Shao , Lihui Chen , Lemao Liu

Knowledge Distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. While contrastive learning has shown promise in self-supervised learning by creating discriminative representations, its…

计算机视觉与模式识别 · 计算机科学 2025-05-14 Nikolaos Giakoumoglou , Tania Stathaki

This thesis aims to investigate the feasibility of knowledge transfer between neural networks for medical image segmentation tasks, specifically focusing on the transfer from a larger multi-task "Teacher" network to a smaller "Student"…

图像与视频处理 · 电气工程与系统科学 2024-06-06 Risab Biswas

Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data…

计算与语言 · 计算机科学 2025-06-02 Jongwoo Ko , Tianyi Chen , Sungnyun Kim , Tianyu Ding , Luming Liang , Ilya Zharkov , Se-Young Yun

This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…

计算与语言 · 计算机科学 2025-11-03 Jiasen Zheng , Huajun Zhang , Xu Yan , Ran Hao , Chong Peng

In real-world systems, models are frequently updated as more data becomes available, and in addition to achieving high accuracy, the goal is to also maintain a low difference in predictions compared to the base model (i.e. predictive…

机器学习 · 计算机科学 2022-03-15 Heinrich Jiang , Harikrishna Narasimhan , Dara Bahri , Andrew Cotter , Afshin Rostamizadeh

Deep learning techniques have achieved great success in many fields, while at the same time deep learning models are getting more complex and expensive to compute. It severely hinders the wide applications of these models. In order to…

计算与语言 · 计算机科学 2021-04-20 Yongqi Li , Wenjie Li

In the past year, distillation has seen a renewed prominence in large language model (LLM) pretraining, exemplified by the Llama-3.2 and Gemma model families. While distillation has historically been shown to improve statistical modeling,…

机器学习 · 计算机科学 2025-09-03 Sachin Goyal , David Lopez-Paz , Kartik Ahuja

In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required…

计算机视觉与模式识别 · 计算机科学 2024-04-18 Zhengyang Liang , Meiyu Liang , Wei Huang , Yawen Li , Zhe Xue

Large-scale contrastive learning models can learn very informative sentence embeddings, but are hard to serve online due to the huge model size. Therefore, they often play the role of "teacher", transferring abilities to small "student"…

人工智能 · 计算机科学 2023-01-31 Chaochen Gao , Xing Wu , Peng Wang , Jue Wang , Liangjun Zang , Zhongyuan Wang , Songlin Hu

The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of…

机器学习 · 计算机科学 2022-09-29 Su Lu , Han-Jia Ye , De-Chuan Zhan

Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep the model fixed and instead attempt to distill the knowledge…

机器学习 · 计算机科学 2020-02-26 Tongzhou Wang , Jun-Yan Zhu , Antonio Torralba , Alexei A. Efros

Knowledge distillation is the procedure of transferring "knowledge" from a large model (the teacher) to a more compact one (the student), often being used in the context of model compression. When both models have the same architecture,…

机器学习 · 计算机科学 2022-06-20 Minh Pham , Minsu Cho , Ameya Joshi , Chinmay Hegde
‹ 上一页 1 2 3 10 下一页 ›