Deep Reinforcement Learning Boosted Partial Domain Adaptation

Domain adaptation is critical for learning transferable features that effectively reduce the distribution difference among domains. In the era of big data, the availability of large-scale labeled datasets motivates partial domain adaptation (PDA) which deals with adaptation from large source domains to small target domains with less number of classes. In the PDA setting, it is crucial to transfer relevant source samples and eliminate irrelevant ones to mitigate negative transfer. In this paper, we propose a deep reinforcement learning based source data selector for PDA, which is capable of eliminating less relevant source samples automatically to boost existing adaptation methods. It determines to either keep or discard the source instances based on their feature representations so that more effective knowledge transfer across domains can be achieved via filtering out irrelevant samples. As a general module, the proposed DRL-based data selector can be integrated into any existing domain adaptation or partial domain adaptation models. Extensive experiments on several benchmark datasets demonstrate the superiority of the proposed DRL-based data selector which leads to state-of-the-art performance for various PDA tasks.

Download Full-text

Exploiting Local Feature Patterns for Unsupervised Domain Adaptation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015401 ◽

2019 ◽

Vol 33 ◽

pp. 5401-5408 ◽

Cited By ~ 6

Author(s):

Jun Wen ◽

Risheng Liu ◽

Nenggan Zheng ◽

Qian Zheng ◽

Zhefeng Gong ◽

...

Keyword(s):

Negative Transfer ◽

Domain Adaptation ◽

Local Feature ◽

Fine Grained ◽

Unsupervised Domain Adaptation ◽

Distribution Matching ◽

Benchmark Datasets ◽

Invariant Representations ◽

Multi Mode ◽

Feature Alignment

Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature alignment by matching source and target holistic feature distributions, without considering local features and their multi-mode statistics. We show that the learned local feature patterns are more generic and transferable and a further local feature distribution matching enables fine-grained feature alignment. In this paper, we present a method for learning domain-invariant local feature patterns and jointly aligning holistic and local feature statistics. Comparisons to the state-of-the-art unsupervised domain adaptation methods on two popular benchmark datasets demonstrate the superiority of our approach and its effectiveness on alleviating negative transfer.

Download Full-text

Unsupervised Domain Adaptation with Coupled Generative Adversarial Autoencoders

Applied Sciences ◽

10.3390/app8122529 ◽

2018 ◽

Vol 8 (12) ◽

pp. 2529 ◽

Cited By ~ 4

Author(s):

Xiaoqing Wang ◽

Xiangjun Wang

Keyword(s):

Neural Network ◽

Image Classification ◽

Large Scale ◽

Domain Adaptation ◽

Generative Adversarial Networks ◽

Class Invariant ◽

Benchmark Datasets ◽

Neural Network Structure ◽

Classification Tasks ◽

High Level

When large-scale annotated data are not available for certain image classification tasks, training a deep convolutional neural network model becomes challenging. Some recent domain adaptation methods try to solve this problem using generative adversarial networks and have achieved promising results. However, these methods are based on a shared latent space assumption and they do not consider the situation when shared high level representations in different domains do not exist or are not ideal as they assumed. To overcome this limitation, we propose a neural network structure called coupled generative adversarial autoencoders (CGAA) that allows a pair of generators to learn the high-level differences between two domains by sharing only part of the high-level layers. Additionally, by introducing a class consistent loss calculated by a stand-alone classifier into the generator optimization, our model is able to generate class invariant style-transferred images suitable for classification tasks in domain adaptation. We apply CGAA to several domain transferred image classification scenarios including several benchmark datasets. Experiment results have shown that our method can achieve state-of-the-art classification results.

Download Full-text

A COMPARISON OF TWO STRATEGIES FOR AVOIDING NEGATIVE TRANSFER IN DOMAIN ADAPTATION BASED ON LOGISTIC REGRESSION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-845-2018 ◽

2018 ◽

Vol XLII-2 ◽

pp. 845-852 ◽

Cited By ~ 1

Author(s):

A. Paul ◽

K. Vogt ◽

F. Rottensteiner ◽

J. Ostermann ◽

C. Heipke

Keyword(s):

Negative Transfer ◽

Domain Adaptation ◽

Classification Performance ◽

Target Domain ◽

Maximum Mean Discrepancy ◽

Source Domain ◽

Training Samples ◽

Benchmark Datasets ◽

Consistent Performance ◽

Class Labels

In this paper we deal with the problem of measuring the similarity between training and tests datasets in the context of transfer learning (TL) for image classification. TL tries to transfer knowledge from a source domain, where labelled training samples are abundant but the data may follow a different distribution, to a target domain, where labelled training samples are scarce or even unavailable, assuming that the domains are related. Thus, the requirements w.r.t. the availability of labelled training samples in the target domain are reduced. In particular, if no labelled target data are available, it is inherently difficult to find a robust measure of relatedness between the source and target domains. This is of crucial importance for the performance of TL, because the knowledge transfer between unrelated data may lead to negative transfer, i.e. to a decrease of classification performance after transfer. We address the problem of measuring the relatedness between source and target datasets and investigate three different strategies to predict and, consequently, to avoid negative transfer in this paper. The first strategy is based on circular validation. The second strategy relies on the Maximum Mean Discrepancy (MMD) similarity metric, whereas the third one is an extension of MMD which incorporates the knowledge about the class labels in the source domain. Our method is evaluated using two different benchmark datasets. The experiments highlight the strengths and weaknesses of the investigated methods. We also show that it is possible to reduce the amount of negative transfer using these strategies for a TL method and to generate a consistent performance improvement over the whole dataset.

Download Full-text

Bayesian Uncertainty Matching for Unsupervised Domain Adaptation

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/534 ◽

2019 ◽

Cited By ~ 4

Author(s):

Jun Wen ◽

Nenggan Zheng ◽

Junsong Yuan ◽

Zhefeng Gong ◽

Changyou Chen

Keyword(s):

Negative Transfer ◽

Domain Adaptation ◽

Target Domain ◽

Bayesian Neural Network ◽

Prediction Uncertainty ◽

Unsupervised Domain Adaptation ◽

Distribution Matching ◽

Benchmark Datasets ◽

Label Distribution ◽

Target Data

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the input features, due to the unavailability of target domain labels. We show that domain shift may still exist via label distribution shift at the classifier, thus deteriorating model performances. To alleviate this issue, we propose an approximate joint distribution matching scheme by exploiting prediction uncertainty. Specifically, we use a Bayesian neural network to quantify prediction uncertainty of a classifier. By imposing distribution matching on both features and labels (via uncertainty), label distribution mismatching in source and target data is effectively alleviated, encouraging the classifier to produce consistent predictions across domains. We also propose a few techniques to improve our method by adaptively reweighting domain adaptation loss to achieve nontrivial distribution matching and stable training. Comparisons with state of the art unsupervised domain adaptation methods on three popular benchmark datasets demonstrate the superiority of our approach, especially on the effectiveness of alleviating negative transfer.

Download Full-text

TUGDA: Task uncertainty guided domain adaptation for robust generalization of cancer drug response prediction from in vitro to in vivo settings

10.1101/2020.12.17.415737 ◽

2020 ◽

Author(s):

Rafael Peres da Silva ◽

Chayaporn Suphavilai ◽

Niranjan Nagarajan

Keyword(s):

Predictive Models ◽

Large Scale ◽

Drug Response ◽

Negative Transfer ◽

Domain Adaptation ◽

Cancer Drug ◽

Data Limitations ◽

The Right

AbstractOver the last decade, large-scale cancer omics studies have highlighted the diversity of patient molecular profiles and the importance of leveraging this information to deliver the right drug to the right patient at the right time. Key challenges in learning predictive models for this include the high-dimensionality of omics data, limitations in the number of data points available, and heterogeneity in biological and clinical factors affecting patient response. The use of multi-task learning (MTL) techniques has been widely explored to address dataset limitations for in vitro drug response models, while domain adaptation (DA) has been employed to extend them to predict in vivo response. In both of these transfer learning settings, noisy data for some tasks (or domains) can substantially reduce the performance for others compared to single-task (domain) learners, i.e. lead to negative transfer (NT). We describe a novel multi-task unsupervised domain adaptation method (TUGDA) that addresses these limitations in a unified framework by quantifying uncertainty in predictors and weighting their influence on shared domain/task feature representations. TUGDA’s ability to rely more on predictors with low-uncertainty allowed it to notably reduce cases of negative transfer for in vitro models (63% for drugs with limited data and 94% overall) compared to state-of-the-art methods. For domain adaptation to in vivo settings, TUGDA improved performance for 6 out of 12 drugs in patient-derived xenografts, and 7 out of 22 drugs in TCGA patient datasets, despite being trained in an unsupervised fashion. TUGDA’s ability to avoid negative transfer thus provides a key capability as we try to integrate diverse drug-response datasets to build consistent predictive models with in vivo utility.Availabilityhttps://github.com/CSB5/TUGDA

Download Full-text

Unsupervised Domain Adaptation on Reading Comprehension

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6245 ◽

2020 ◽

Vol 34 (05) ◽

pp. 7480-7487

Author(s):

Yu Cao ◽

Meng Fang ◽

Baosheng Yu ◽

Joey Tianyi Zhou

Keyword(s):

Reading Comprehension ◽

Large Scale ◽

Domain Adaptation ◽

Generalization Capability ◽

Target Domain ◽

Adversarial Learning ◽

Unsupervised Domain Adaptation ◽

Comparable Performance ◽

Benchmark Datasets ◽

Contextual Representation

Reading comprehension (RC) has been studied in a variety of datasets with the boosted performance brought by deep neural networks. However, the generalization capability of these models across different domains remains unclear. To alleviate the problem, we investigate unsupervised domain adaptation on RC, wherein a model is trained on the labeled source domain and to be applied to the target domain with only unlabeled samples. We first show that even with the powerful BERT contextual representation, a model can not generalize well from one domain to another. To solve this, we provide a novel conditional adversarial self-training method (CASe). Specifically, our approach leverages a BERT model fine-tuned on the source dataset along with the confidence filtering to generate reliable pseudo-labeled samples in the target domain for self-training. On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains. Extensive experiments show our approach achieves comparable performance to supervised models on multiple large-scale benchmark datasets.

Download Full-text