English
Related papers

Related papers: Quantum-Gated Task-interaction Knowledge Distillat…

200 papers

Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from…

Machine Learning · Computer Science 2024-01-18 Rishabh Agarwal , Nino Vieillard , Yongchao Zhou , Piotr Stanczyk , Sabela Ramos , Matthieu Geist , Olivier Bachem

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few…

Computation and Language · Computer Science 2024-04-03 Kailin Zhao , Xiaolong Jin , Long Bai , Jiafeng Guo , Xueqi Cheng

Class Incremental Learning (CIL) aims to sequentially acquire knowledge of new classes without forgetting previously learned ones. Despite recent progress, current CIL methods still exhibit significant performance gaps compared to their…

Machine Learning · Computer Science 2025-09-29 Zihuan Qiu , Yi Xu , Fanman Meng , Runtong Zhang , Linfeng Xu , Qingbo Wu , Hongliang Li

Knowledge Distillation (KD) refers to transferring knowledge from a large model to a smaller one, which is widely used to enhance model performance in machine learning. It tries to align embedding spaces generated from the teacher and the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Weidong Shi , Guanghui Ren , Yunpeng Chen , Shuicheng Yan

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Mingsheng Li , Lin Zhang , Mingzhen Zhu , Zilong Huang , Gang Yu , Jiayuan Fan , Tao Chen

Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales, hallucinated supervision, and static teacher-student interactions. Existing reasoning…

Computation and Language · Computer Science 2026-05-14 Kasidit Sermsri , Teerapong Panboonyuen

Recent advances in knowledge distillation (KD) predominantly emphasize feature-level knowledge transfer, frequently overlooking critical information embedded within the teacher's logit distributions. In this paper, we revisit logit-based…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Qi Wang , Jinjia Zhou

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) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Mengya Gao , Yujun Shen , Quanquan Li , Junjie Yan , Liang Wan , Dahua Lin , Chen Change Loy , Xiaoou Tang

Recently, various intermediate layer distillation (ILD) objectives have been shown to improve compression of BERT models via Knowledge Distillation (KD). However, a comprehensive evaluation of the objectives in both task-specific and…

Computation and Language · Computer Science 2023-05-25 Xinpeng Wang , Leonie Weissweiler , Hinrich Schütze , Barbara Plank

Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model. Despite the success of KD in the classification task, applying KD to recommender models is…

Machine Learning · Computer Science 2019-11-14 Jae-woong Lee , Minjin Choi , Jongwuk Lee , Hyunjung Shim

Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Efstathia Soufleri , Deepak Ravikumar , Kaushik Roy

Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed pre-impact fall detection systems using deep learning to support wearable-based fall protection systems for preventing severe injuries.…

Signal Processing · Electrical Eng. & Systems 2023-03-30 Tin-Han Chi , Kai-Chun Liu , Chia-Yeh Hsieh , Yu Tsao , Chia-Tai Chan

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model. Existing efforts guide the distillation by matching their prediction logits, feature embedding, etc., while leaving…

Computer Vision and Pattern Recognition · Computer Science 2022-12-01 Yiyang Liu , Chenxin Li , Xiaotong Tu , Xinghao Ding , Yue Huang

Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing computational and storage costs while maintaining competitive accuracy.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Fengming Yu , Haiwei Pan , Kejia Zhang , Jian Guan , Haiying Jiang

Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past. This strict restriction enlarges the difficulty of alleviating catastrophic forgetting since all techniques…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Jiang-Tian Zhai , Xialei Liu , Lu Yu , Ming-Ming Cheng

Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of…

Computer Vision and Pattern Recognition · Computer Science 2020-01-17 Junting Zhang , Jie Zhang , Shalini Ghosh , Dawei Li , Serafettin Tasci , Larry Heck , Heming Zhang , C. -C. Jay Kuo

We propose a novel approach for class incremental online learning in a limited data setting. This problem setting is challenging because of the following constraints: (1) Classes are given incrementally, which necessitates a class…

Machine Learning · Computer Science 2021-06-15 Mohammed Asad Karim , Vinay Kumar Verma , Pravendra Singh , Vinay Namboodiri , Piyush Rai

Class-incremental Learning (CIL) enables the model to incrementally absorb knowledge from new classes and build a generic classifier across all previously encountered classes. When the model optimizes with new classes, the knowledge of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Juncen Guo , Xiaoguang Zhu , Liangyu Teng , Hao Yang , Jing Liu , Yang Liu , Liang Song

In this paper, we present the ``joint pre-training and local re-training'' framework for learning and applying multi-source knowledge graph (KG) embeddings. We are motivated by the fact that different KGs contain complementary information…

Computation and Language · Computer Science 2023-06-06 Zequn Sun , Jiacheng Huang , Jinghao Lin , Xiaozhou Xu , Qijin Chen , Wei Hu