Does Decentralized Learning with Non-IID Unlabeled Data Benefit from Self Supervision?

• URL: http://arxiv.org/abs/2210.10947v1
• Date: Thu, 20 Oct 2022 01:32:41 GMT
• Title: Does Decentralized Learning with Non-IID Unlabeled Data Benefit from Self Supervision?
• Authors: Lirui Wang, Kaiqing Zhang, Yunzhu Li, Yonglong Tian, Russ Tedrake
• Abstract summary: We study decentralized learning with unlabeled data through the lens of self-supervised learning (SSL) We study the effectiveness of contrastive learning algorithms under decentralized learning settings.
• Score: 51.00034621304361
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decentralized learning has been advocated and widely deployed to make efficient use of distributed datasets, with an extensive focus on supervised learning (SL) problems. Unfortunately, the majority of real-world data are unlabeled and can be highly heterogeneous across sources. In this work, we carefully study decentralized learning with unlabeled data through the lens of self-supervised learning (SSL), specifically contrastive visual representation learning. We study the effectiveness of a range of contrastive learning algorithms under decentralized learning settings, on relatively large-scale datasets including ImageNet-100, MS-COCO, and a new real-world robotic warehouse dataset. Our experiments show that the decentralized SSL (Dec-SSL) approach is robust to the heterogeneity of decentralized datasets, and learns useful representation for object classification, detection, and segmentation tasks. This robustness makes it possible to significantly reduce communication and reduce the participation ratio of data sources with only minimal drops in performance. Interestingly, using the same amount of data, the representation learned by Dec-SSL can not only perform on par with that learned by centralized SSL which requires communication and excessive data storage costs, but also sometimes outperform representations extracted from decentralized SL which requires extra knowledge about the data labels. Finally, we provide theoretical insights into understanding why data heterogeneity is less of a concern for Dec-SSL objectives, and introduce feature alignment and clustering techniques to develop a new Dec-SSL algorithm that further improves the performance, in the face of highly non-IID data. Our study presents positive evidence to embrace unlabeled data in decentralized learning, and we hope to provide new insights into whether and why decentralized SSL is effective.

Related papers

• A Survey of the Self Supervised Learning Mechanisms for Vision Transformers [5.152455218955949]
  The application of self supervised learning (SSL) in vision tasks has gained significant attention. We develop a comprehensive taxonomy of systematically classifying the SSL techniques. We discuss the motivations behind SSL, review popular pre-training tasks, and highlight the challenges and advancements in this field.
  arXiv  Detail & Related papers  (2024-08-30T07:38:28Z)
• What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights [67.72413262980272]
  Severe data imbalance naturally exists among web-scale vision-language datasets. We find CLIP pre-trained thereupon exhibits notable robustness to the data imbalance compared to supervised learning. The robustness and discriminability of CLIP improve with more descriptive language supervision, larger data scale, and broader open-world concepts.
  arXiv  Detail & Related papers  (2024-05-31T17:57:24Z)
• Language Semantic Graph Guided Data-Efficient Learning [10.039953846594805]
  We introduce a Language Semantic Graph (LSG) which is constructed from labels manifest as natural language descriptions. An auxiliary graph neural network is trained to extract high-level semantic relations and then used to guide the training of the primary model. Our in-depth analysis shows that the LSG method also expedites the training process.
  arXiv  Detail & Related papers  (2023-11-15T08:54:57Z)
• Towards Realistic Semi-Supervised Learning [73.59557447798134]
  We propose a novel approach to tackle SSL in open-world setting, where we simultaneously learn to classify known and unknown classes. Our approach substantially outperforms the existing state-of-the-art on seven diverse datasets.
  arXiv  Detail & Related papers  (2022-07-05T19:04:43Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)
• FedSEAL: Semi-Supervised Federated Learning with Self-Ensemble Learning and Negative Learning [7.771967424619346]
  Federated learning (FL) is a popular decentralized and privacy-preserving machine learning (FL) framework. In this paper, we propose a new FL algorithm, called FedSEAL, to solve this Semi-Supervised Federated Learning (SSFL) problem. Our algorithm utilizes self-ensemble learning and complementary negative learning to enhance both the accuracy and the efficiency of clients' unsupervised learning on unlabeled data.
  arXiv  Detail & Related papers  (2021-10-15T03:03:23Z)
• Self-supervised Learning is More Robust to Dataset Imbalance [65.84339596595383]
  We investigate self-supervised learning under dataset imbalance. Off-the-shelf self-supervised representations are already more robust to class imbalance than supervised representations. We devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets.
  arXiv  Detail & Related papers  (2021-10-11T06:29:56Z)
• Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data [77.88594632644347]
  Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization challenge. We propose a novel momentum-based method to mitigate this decentralized training difficulty.
  arXiv  Detail & Related papers  (2021-02-09T11:27:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.