Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation

• URL: http://arxiv.org/abs/2307.05948v1
• Date: Wed, 12 Jul 2023 06:29:02 GMT
• Title: Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation
• Authors: Ruijiang Dong, Feng Liu, Haoang Chi, Tongliang Liu, Mingming Gong, Gang Niu, Masashi Sugiyama and Bo Han
• Abstract summary: We propose a diversity-enhancing generative network (DEG-Net) for the FHA problem. It can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC)
• Score: 135.80439360370556
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating unlabeled data has been recently shown to help address the few-shot hypothesis adaptation (FHA) problem, where we aim to train a classifier for the target domain with a few labeled target-domain data and a well-trained source-domain classifier (i.e., a source hypothesis), for the additional information of the highly-compatible unlabeled data. However, the generated data of the existing methods are extremely similar or even the same. The strong dependency among the generated data will lead the learning to fail. In this paper, we propose a diversity-enhancing generative network (DEG-Net) for the FHA problem, which can generate diverse unlabeled data with the help of a kernel independence measure: the Hilbert-Schmidt independence criterion (HSIC). Specifically, DEG-Net will generate data via minimizing the HSIC value (i.e., maximizing the independence) among the semantic features of the generated data. By DEG-Net, the generated unlabeled data are more diverse and more effective for addressing the FHA problem. Experimental results show that the DEG-Net outperforms existing FHA baselines and further verifies that generating diverse data plays a vital role in addressing the FHA problem

Related papers

• Federated Causal Discovery from Heterogeneous Data [70.31070224690399]
  We propose a novel FCD method attempting to accommodate arbitrary causal models and heterogeneous data. These approaches involve constructing summary statistics as a proxy of the raw data to protect data privacy. We conduct extensive experiments on synthetic and real datasets to show the efficacy of our method.
  arXiv  Detail & Related papers  (2024-02-20T18:53:53Z)
• Federated Learning Empowered by Generative Content [55.576885852501775]
  Federated learning (FL) enables leveraging distributed private data for model training in a privacy-preserving way. We propose a novel FL framework termed FedGC, designed to mitigate data heterogeneity issues by diversifying private data with generative content. We conduct a systematic empirical study on FedGC, covering diverse baselines, datasets, scenarios, and modalities.
  arXiv  Detail & Related papers  (2023-12-10T07:38:56Z)
• Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks [65.34113135080105]
  We show that not only the issue of data heterogeneity in current setups is not necessarily a problem but also in fact it can be beneficial for the FL participants. Our observations are intuitive. Our code is available at https://github.com/MMorafah/FL-SC-NIID.
  arXiv  Detail & Related papers  (2022-09-30T17:15:19Z)
• Mitigating Data Heterogeneity in Federated Learning with Data Augmentation [26.226057709504733]
  Federated Learning (FL) is a framework that enables training a centralized model while securing user privacy by fusing local, decentralized models. One major obstacle is data heterogeneity, i.e., each client having non-identically and independently distributed (non-IID) data. Recent evidence suggests that data augmentation can induce equal or greater performance.
  arXiv  Detail & Related papers  (2022-06-20T19:47:43Z)
• Improving the quality of generative models through Smirnov transformation [1.3492000366723798]
  We propose a novel activation function to be used as output of the generator agent. It is based on the Smirnov probabilistic transformation and it is specifically designed to improve the quality of the generated data.
  arXiv  Detail & Related papers  (2021-10-29T17:01:06Z)
• TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation [73.75784418508033]
  In few-shot domain adaptation (FDA), classifiers for the target domain are trained with labeled data in the source domain (SD) and few labeled data in the target domain (TD) Data usually contain private information in the current era, e.g., data distributed on personal phones. We propose a target orientated hypothesis adaptation network (TOHAN) to solve the problem.
  arXiv  Detail & Related papers  (2021-06-11T11:46:20Z)
• Domain Adaptation for Learning Generator from Paired Few-Shot Data [72.04430033118426]
  We propose a Paired Few-shot GAN (PFS-GAN) model for learning generators with sufficient source data and a few target data. Our method has better quantitative and qualitative results on the generated target-domain data with higher diversity in comparison to several baselines.
  arXiv  Detail & Related papers  (2021-02-25T10:11:44Z)
• Discriminative feature generation for classification of imbalanced data [6.458496335718508]
  We propose a novel supervised discriminative feature generation (DFG) method for a minority class dataset. DFG is based on the modified structure of a generative adversarial network consisting of four independent networks. The experimental results show that the DFG generator enhances the augmentation of the label-preserved and diverse features.
  arXiv  Detail & Related papers  (2020-10-24T12:19:05Z)
• Towards Stable Imbalanced Data Classification via Virtual Big Data Projection [3.3707422585608953]
  We investigate the capability of VBD to address deep autoencoder training and imbalanced data classification. First, we prove that, VBD can significantly decrease the validation loss of autoencoders via providing them a huge diversified training data. Second, we propose the first projection-based method called cross-concatenation to balance the skewed class distributions without over-sampling.
  arXiv  Detail & Related papers  (2020-08-23T04:01:51Z)

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.