English
Related papers

Related papers: Iterative Graph Self-Distillation

200 papers

This paper introduces a novel approach that integrates graph theory into self-supervised representation learning. Traditional methods focus on intra-instance variations generated by applying augmentations. However, they often overlook…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Ali Javidani , Babak Nadjar Araabi , Mohammad Amin Sadeghi

Pothole classification has become an important task for road inspection vehicles to save drivers from potential car accidents and repair bills. Given the limited computational power and fixed number of training epochs, we propose iterative…

Computer Vision and Pattern Recognition · Computer Science 2022-02-07 Kuan-Chuan Peng

We present a simple but effective pixel-level self-supervised distillation framework friendly to dense prediction tasks. Our method, called Pixel-Wise Contrastive Distillation (PCD), distills knowledge by attracting the corresponding pixels…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Junqiang Huang , Zichao Guo

While the success of deep learning relies on large amounts of training datasets, data is often limited in privacy-sensitive domains. To address this challenge, generative model learning with differential privacy has emerged as a solution to…

Machine Learning · Computer Science 2024-08-28 Bochao Liu , Pengju Wang , Shiming Ge

We present a novel adversarial penalized self-knowledge distillation method, named adversarial learning and implicit regularization for self-knowledge distillation (AI-KD), which regularizes the training procedure by adversarial learning…

Computer Vision and Pattern Recognition · Computer Science 2024-03-22 Hyungmin Kim , Sungho Suh , Sunghyun Baek , Daehwan Kim , Daun Jeong , Hansang Cho , Junmo Kim

Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years. However, the problem of insufficient supervision, together with representation collapse, largely limits the performance…

Machine Learning · Computer Science 2025-03-07 Xihong Yang , Yiqi Wang , Yue Liu , Yi Wen , Lingyuan Meng , Sihang Zhou , Xinwang Liu , En Zhu

In this paper, we address the problem of distillation-based class-incremental learning with a single head. A central theme of this task is to learn new classes that arrive in sequential phases over time while keeping the model's capability…

Computer Vision and Pattern Recognition · Computer Science 2021-01-25 Cheng-Hsun Lei , Yi-Hsin Chen , Wen-Hsiao Peng , Wei-Chen Chiu

Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately. However, existing methods…

Computation and Language · Computer Science 2023-10-24 Yichuan Li , Kaize Ding , Kyumin Lee

Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have attracted increasing concerns. Existing graph condensation methods primarily focus on optimizing the feature…

Machine Learning · Computer Science 2023-10-16 Beining Yang , Kai Wang , Qingyun Sun , Cheng Ji , Xingcheng Fu , Hao Tang , Yang You , Jianxin Li

Dataset distillation enables the training of deep neural networks with comparable performance in significantly reduced time by compressing large datasets into small and representative ones. Although the introduction of generative models has…

Machine Learning · Computer Science 2025-05-27 Mingzhuo Li , Guang Li , Jiafeng Mao , Takahiro Ogawa , Miki Haseyama

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Zhizhong Li , Avinash Ravichandran , Charless Fowlkes , Marzia Polito , Rahul Bhotika , Stefano Soatto

Using huge training datasets can be costly and inconvenient. This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest…

Machine Learning · Computer Science 2022-03-17 Dmitry Medvedev , Alexander D'yakonov

Knowledge distillation is widely adopted in semantic segmentation to reduce the computation cost.The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Zhengbo Zhang , Chunluan Zhou , Zhigang Tu

Self-supervised learning (SSL) on graphs generates node and graph representations (i.e., embeddings) that can be used for downstream tasks such as node classification, node clustering, and link prediction. Graph SSL is particularly useful…

Machine Learning · Computer Science 2025-09-26 Jiali Chen , Avijit Mukherjee

Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network. As an effective teaching strategy, interactive teaching has been…

Computer Vision and Pattern Recognition · Computer Science 2021-04-16 Shipeng Fu , Zhen Li , Jun Xu , Ming-Ming Cheng , Zitao Liu , Xiaomin Yang

Contrastive learning has shown great promise in the field of graph representation learning. By manually constructing positive/negative samples, most graph contrastive learning methods rely on the vector inner product based similarity metric…

Machine Learning · Computer Science 2022-07-27 Yuehui Han , Le Hui , Haobo Jiang , Jianjun Qian , Jin Xie

Knowledge distillation (KD) is essentially a process of transferring a teacher model's behavior, e.g., network response, to a student model. The network response serves as additional supervision to formulate the machine domain, which uses…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Yulei Niu , Long Chen , Chang Zhou , Hanwang Zhang

Federated learning (FL) enables multiple clients to collaboratively train a global model while keeping local data decentralized. Data heterogeneity (non-IID) across clients has imposed significant challenges to FL, which makes local models…

Machine Learning · Computer Science 2025-04-22 Yuting He , Yiqiang Chen , XiaoDong Yang , Hanchao Yu , Yi-Hua Huang , Yang Gu

Knowledge distillation provides an effective way to transfer knowledge via teacher-student learning, where most existing distillation approaches apply a fixed pre-trained model as teacher to supervise the learning of student network. This…

Machine Learning · Computer Science 2021-03-26 Kangkai Zhang , Chunhui Zhang , Shikun Li , Dan Zeng , Shiming Ge

Deep learning on graphs has recently achieved remarkable success on a variety of tasks, while such success relies heavily on the massive and carefully labeled data. However, precise annotations are generally very expensive and…

Machine Learning · Computer Science 2021-09-30 Lirong Wu , Haitao Lin , Zhangyang Gao , Cheng Tan , Stan. Z. Li
‹ Prev 1 4 5 6 7 8 10 Next ›