English
Related papers

Related papers: Learning Generalizable Models for Vehicle Routing …

200 papers

Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by…

Computer Vision and Pattern Recognition · Computer Science 2024-09-06 Hyungkeun Park , Jong-Seok Lee

Knowledge Distillation (KD) is a model compression algorithm that helps transfer the knowledge of a large neural network into a smaller one. Even though KD has shown promise on a wide range of Natural Language Processing (NLP) applications,…

Computation and Language · Computer Science 2021-09-21 Tianda Li , Ahmad Rashid , Aref Jafari , Pranav Sharma , Ali Ghodsi , Mehdi Rezagholizadeh

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

Software Engineering · Computer Science 2025-08-22 Ruiqi Wang , Zezhou Yang , Cuiyun Gao , Xin Xia , Qing Liao

Knowledge distillation~(KD) is an effective learning paradigm for improving the performance of lightweight student networks by utilizing additional supervision knowledge distilled from teacher networks. Most pioneering studies either learn…

Computer Vision and Pattern Recognition · Computer Science 2021-03-09 Yuang Liu , Wei Zhang , Jun Wang

In recent years the empirical success of transfer learning with neural networks has stimulated an increasing interest in obtaining a theoretical understanding of its core properties. Knowledge distillation where a smaller neural network is…

Machine Learning · Computer Science 2022-11-11 Luca Saglietti , Lenka Zdeborová

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically using forward Kullback-Leibler divergence (FKLD) or reverse KLD…

Machine Learning · Computer Science 2025-06-04 Guanghui Wang , Zhiyong Yang , Zitai Wang , Shi Wang , Qianqian Xu , Qingming Huang

Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression. While knowledge distillation (KD) is a prominent method for this, research on KD for…

Computation and Language · Computer Science 2024-09-30 Gyeongman Kim , Doohyuk Jang , Eunho Yang

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In…

Machine Learning · Computer Science 2020-04-08 Sukmin Yun , Jongjin Park , Kimin Lee , Jinwoo Shin

Dense visual prediction tasks, such as detection and segmentation, are crucial for time-critical applications (e.g., autonomous driving and video surveillance). While deep models achieve strong performance, their efficiency remains a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Qizhen Lan , Qing Tian

Deep pre-training and fine-tuning models (such as BERT and OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow.…

Computation and Language · Computer Science 2019-10-21 Ze Yang , Linjun Shou , Ming Gong , Wutao Lin , Daxin Jiang

Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is quite promising to…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Jangho Kim , Yash Bhalgat , Jinwon Lee , Chirag Patel , Nojun Kwak

Knowledge distillation as a broad class of methods has led to the development of lightweight and memory efficient models, using a pre-trained model with a large capacity (teacher network) to train a smaller model (student network).…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Eun Som Jeon , Hongjun Choi , Ankita Shukla , Pavan Turaga

In recent years, deep learning has spread rapidly, and deeper, larger models have been proposed. However, the calculation cost becomes enormous as the size of the models becomes larger. Various techniques for compressing the size of the…

Machine Learning · Computer Science 2020-04-20 Hideki Oki , Motoshi Abe , Junichi Miyao , Takio Kurita

Knowledge Distillation (KD) is a strategy for the definition of a set of transferability gangways to improve the efficiency of Convolutional Neural Networks. Feature-based Knowledge Distillation is a subfield of KD that relies on…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Alejandro López-Cifuentes , Marcos Escudero-Viñolo , Jesús Bescós , Juan C. SanMiguel

Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained language models. However, intermediate layer distillation…

Computation and Language · Computer Science 2021-10-05 Md Akmal Haidar , Nithin Anchuri , Mehdi Rezagholizadeh , Abbas Ghaddar , Philippe Langlais , Pascal Poupart

The proliferation of foundation models, pretrained on large-scale unlabeled datasets, has emerged as an effective approach in creating adaptable and reusable architectures that can be leveraged for various downstream tasks using satellite…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Abdul Matin , Tanjim Bin Faruk , Shrideep Pallickara , Sangmi Lee Pallickara

Deep models trained on long-tailed datasets exhibit unsatisfactory performance on tail classes. Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-22 Shaoyu Zhang , Chen Chen , Xiyuan Hu , Silong Peng

Knowledge Distillation (KD) aims at transferring knowledge from a larger well-optimized teacher network to a smaller learnable student network.Existing KD methods have mainly considered two types of knowledge, namely the individual…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Sheng Zhou , Yucheng Wang , Defang Chen , Jiawei Chen , Xin Wang , Can Wang , Jiajun Bu

In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our Dynamic Guidance Adversarial Distillation (DGAD) framework…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Hyejin Park , Dongbo Min

Data-free Knowledge Distillation (DFKD) is a method that constructs pseudo-samples using a generator without real data, and transfers knowledge from a teacher model to a student by enforcing the student to overcome dimensional differences…

Machine Learning · Computer Science 2025-04-03 Yuang Jia , Xiaojuan Shan , Jun Xia , Guancheng Wan , Yuchen Zhang , Wenke Huang , Mang Ye , Stan Z. Li