Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data

• URL: http://arxiv.org/abs/2311.01420v1
• Date: Thu, 2 Nov 2023 17:35:16 GMT
• Title: Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
• Authors: Cheng-Hao Tu, Hong-You Chen, Zheda Mai, Jike Zhong, Vardaan Pahuja, Tanya Berger-Wolf, Song Gao, Charles Stewart, Yu Su, Wei-Lun Chao
• Abstract summary: We propose a learning problem involving adapting a pre-trained source model to the target domain for classifying all classes that appeared in the source data. This problem is practical, as it is unrealistic for the target end-users to collect data for all classes prior to adaptation. We present several effective solutions that maintain the accuracy of the missing classes and enhance the overall performance.
• Score: 32.91362206231936
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose a learning problem involving adapting a pre-trained source model to the target domain for classifying all classes that appeared in the source data, using target data that covers only a partial label space. This problem is practical, as it is unrealistic for the target end-users to collect data for all classes prior to adaptation. However, it has received limited attention in the literature. To shed light on this issue, we construct benchmark datasets and conduct extensive experiments to uncover the inherent challenges. We found a dilemma -- on the one hand, adapting to the new target domain is important to claim better performance; on the other hand, we observe that preserving the classification accuracy of classes missing in the target adaptation data is highly challenging, let alone improving them. To tackle this, we identify two key directions: 1) disentangling domain gradients from classification gradients, and 2) preserving class relationships. We present several effective solutions that maintain the accuracy of the missing classes and enhance the overall performance, establishing solid baselines for holistic transfer of pre-trained models with partial target data.

Related papers

• Decoupling the Class Label and the Target Concept in Machine Unlearning [81.69857244976123]
  Machine unlearning aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previous studies showed that class-wise unlearning is successful in forgetting the knowledge of a target class. We propose a general framework, namely, TARget-aware Forgetting (TARF)
  arXiv  Detail & Related papers  (2024-06-12T14:53:30Z)
• Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation [80.1412989006262]
  Domain adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. We propose T2S-DA, which we interpret as a form of pulling Target to Source for Domain Adaptation.
  arXiv  Detail & Related papers  (2023-05-23T07:09:09Z)
• Mention Annotations Alone Enable Efficient Domain Adaptation for Coreference Resolution [8.08448832546021]
  We show that annotating mentions alone is nearly twice as fast as annotating full coreference chains. Our approach facilitates annotation-efficient transfer and results in a 7-14% improvement in average F1 without increasing annotator time.
  arXiv  Detail & Related papers  (2022-10-14T07:57:27Z)
• MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation [71.4942277262067]
  We propose MemSAC, which exploits sample level similarity across source and target domains to achieve discriminative transfer. We provide in-depth analysis and insights into the effectiveness of MemSAC.
  arXiv  Detail & Related papers  (2022-07-25T17:55:28Z)
• Labeling Where Adapting Fails: Cross-Domain Semantic Segmentation with Point Supervision via Active Selection [81.703478548177]
  Training models dedicated to semantic segmentation require a large amount of pixel-wise annotated data. Unsupervised domain adaptation approaches aim at aligning the feature distributions between the labeled source and the unlabeled target data. Previous works attempted to include human interactions in this process under the form of sparse single-pixel annotations in the target data. We propose a new domain adaptation framework for semantic segmentation with annotated points via active selection.
  arXiv  Detail & Related papers  (2022-06-01T01:52:28Z)
• On Universal Black-Box Domain Adaptation [53.7611757926922]
  We study an arguably least restrictive setting of domain adaptation in a sense of practical deployment. Only the interface of source model is available to the target domain, and where the label-space relations between the two domains are allowed to be different and unknown. We propose to unify them into a self-training framework, regularized by consistency of predictions in local neighborhoods of target samples.
  arXiv  Detail & Related papers  (2021-04-10T02:21:09Z)
• Weak Adaptation Learning -- Addressing Cross-domain Data Insufficiency with Weak Annotator [2.8672054847109134]
  In some target problem domains, there are not many data samples available, which could hinder the learning process. We propose a weak adaptation learning (WAL) approach that leverages unlabeled data from a similar source domain. Our experiments demonstrate the effectiveness of our approach in learning an accurate classifier with limited labeled data in the target domain.
  arXiv  Detail & Related papers  (2021-02-15T06:19:25Z)
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer [137.36099660616975]
  Unsupervised adaptation adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to the source data.
  arXiv  Detail & Related papers  (2020-12-14T07:28:50Z)
• Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation [32.93934837792708]
  We consider the problem of recommendation on sparse implicit feedbacks as a semi-supervised learning task. We focus on the most challenging case -- there is no user or item overlap. We adopt domain-invariant textual features as the anchor points to align the latent spaces.
  arXiv  Detail & Related papers  (2020-06-28T05:28:05Z)
• Progressive Graph Learning for Open-Set Domain Adaptation [48.758366879597965]
  Domain shift is a fundamental problem in visual recognition which typically arises when the source and target data follow different distributions. In this paper, we tackle a more realistic problem of open-set domain shift where the target data contains additional classes that are not present in the source data. We introduce an end-to-end Progressive Graph Learning framework where a graph neural network with episodic training is integrated to suppress underlying conditional shift.
  arXiv  Detail & Related papers  (2020-06-22T09:10:34Z)

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.