Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation

• URL: http://arxiv.org/abs/2411.07185v1
• Date: Mon, 11 Nov 2024 17:59:21 GMT
• Title: Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation
• Authors: Yao Ma, Samuel Louvan, Zhunxuan Wang,
• Abstract summary: Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model. We introduce a framework for gradual fine tuning (GFT) of machine learning models on multiple source domains.
• Score: 5.125509132300994
• License:
• Abstract: Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role in determining the model's performance. It relies on the similarities amongst source and target domains. Nonetheless, existing work for source domain selection often involves heavyweight computational procedures, especially when dealing with numerous source domains and the need to identify the best ones from them. In this paper, we introduce a framework for gradual fine tuning (GFT) of machine learning models on multiple source domains. We represent multiple source domains as an undirected weighted graph. We then give a new generalization error bound for GFT along any path within the graph, which is used to determine the optimal path corresponding to the optimal training order. With this formulation, we introduce three lightweight graph-routing strategies which tend to minimize the error bound. Our best strategy improves $2.3\%$ of accuracy over the state-of-the-art on Natural Language Inference (NLI) task and achieves competitive performance on Sentiment Analysis (SA) task, especially a $3.9\%$ improvement on a more diverse subset of data we use for SA.

Related papers

• Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling [35.39202826643388]
  We present the framework Selective Multi-source Adaptation for Graph (method), with a graph-modeling-based domain selector, a sub-graph node selector, and a bi-level alignment objective. Results on five graph datasets show the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2024-06-14T22:05:21Z)
• Noisy Universal Domain Adaptation via Divergence Optimization for Visual Recognition [30.31153237003218]
  A novel scenario named Noisy UniDA is proposed to transfer knowledge from a labeled source domain to an unlabeled target domain. A multi-head convolutional neural network framework is proposed to address all of the challenges faced in the Noisy UniDA at once.
  arXiv  Detail & Related papers  (2023-04-20T14:18:38Z)
• Improving Multi-Domain Generalization through Domain Re-labeling [31.636953426159224]
  We study the important link between pre-specified domain labels and the generalization performance. We introduce a general approach for multi-domain generalization, MulDEns, that uses an ERM-based deep ensembling backbone. We show that MulDEns does not require tailoring the augmentation strategy or the training process specific to a dataset.
  arXiv  Detail & Related papers  (2021-12-17T23:21:50Z)
• Domain Adaptive Semantic Segmentation without Source Data [50.18389578589789]
  We investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain. We propose an effective framework for this challenging problem with two components: positive learning and negative learning. Our framework can be easily implemented and incorporated with other methods to further enhance the performance.
  arXiv  Detail & Related papers  (2021-10-13T04:12:27Z)
• Dynamic Transfer for Multi-Source Domain Adaptation [82.54405157719641]
  We present dynamic transfer to address domain conflicts, where the model parameters are adapted to samples. It breaks down source domain barriers and turns multi-source domains into a single-source domain. Experimental results show that, without using domain labels, our dynamic transfer outperforms the state-of-the-art method by more than 3%.
  arXiv  Detail & Related papers  (2021-03-19T01:22:12Z)
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation [81.07994783143533]
  Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. In many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
  arXiv  Detail & Related papers  (2020-09-01T00:06:50Z)
• Learning Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation with Few Labeled Source Samples [65.55521019202557]
  Domain adaptation aims to generalize a model from a source domain to tackle tasks in a related but different target domain. Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain. We propose a Domain-invariant Graph Learning (DGL) approach for domain adaptation with only a few labeled source samples.
  arXiv  Detail & Related papers  (2020-08-21T08:13:25Z)
• Multi-source Attention for Unsupervised Domain Adaptation [15.900069711477542]
  We model source-selection as an attention-learning problem, where we learn attention over sources for a given target instance. For this purpose, we first independently learn source-specific classification models, and a relatedness map between sources and target domains. We then learn attention-weights over the sources for aggregating the predictions of the source-specific models.
  arXiv  Detail & Related papers  (2020-04-14T15:51:02Z)
• Deep Domain-Adversarial Image Generation for Domain Generalisation [115.21519842245752]
  Machine learning models typically suffer from the domain shift problem when trained on a source dataset and evaluated on a target dataset of different distribution. To overcome this problem, domain generalisation (DG) methods aim to leverage data from multiple source domains so that a trained model can generalise to unseen domains. We propose a novel DG approach based on emphDeep Domain-Adversarial Image Generation (DDAIG)
  arXiv  Detail & Related papers  (2020-03-12T23:17:47Z)
• Supervised Domain Adaptation using Graph Embedding [86.3361797111839]
  Domain adaptation methods assume that distributions between the two domains are shifted and attempt to realign them. We propose a generic framework based on graph embedding. We show that the proposed approach leads to a powerful Domain Adaptation framework.
  arXiv  Detail & Related papers  (2020-03-09T12:25:13Z)

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.