2022-10-01 更新
On the Convergence of AdaGrad on $\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
Authors:Zijian Liu, Ta Duy Nguyen, Alina Ene, Huy L. Nguyen
Existing analysis of AdaGrad and other adaptive methods for smooth convex optimization is typically for functions with bounded domain diameter. In unconstrained problems, previous works guarantee an asymptotic convergence rate without an explicit constant factor that holds true for the entire function class. Furthermore, in the stochastic setting, only a modified version of AdaGrad, different from the one commonly used in practice, in which the latest gradient is not used to update the stepsize, has been analyzed. Our paper aims at bridging these gaps and developing a deeper understanding of AdaGrad and its variants in the standard setting of smooth convex functions as well as the more general setting of quasar convex functions. First, we demonstrate new techniques to explicitly bound the convergence rate of the vanilla AdaGrad for unconstrained problems in both deterministic and stochastic settings. Second, we propose a variant of AdaGrad for which we can show the convergence of the last iterate, instead of the average iterate. Finally, we give new accelerated adaptive algorithms and their convergence guarantee in the deterministic setting with explicit dependency on the problem parameters, improving upon the asymptotic rate shown in previous works.
PDF
点此查看论文截图
Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretability
Authors:Yan Kang, Yang Liu, Yuezhou Wu, Guoqiang Ma, Qiang Yang
We present a novel privacy-preserving federated adversarial domain adaptation approach ($\textbf{PrADA}$) to address an under-studied but practical cross-silo federated domain adaptation problem, in which the party of the target domain is insufficient in both samples and features. We address the lack-of-feature issue by extending the feature space through vertical federated learning with a feature-rich party and tackle the sample-scarce issue by performing adversarial domain adaptation from the sample-rich source party to the target party. In this work, we focus on financial applications where interpretability is critical. However, existing adversarial domain adaptation methods typically apply a single feature extractor to learn feature representations that are low-interpretable with respect to the target task. To improve interpretability, we exploit domain expertise to split the feature space into multiple groups that each holds relevant features, and we learn a semantically meaningful high-order feature from each feature group. In addition, we apply a feature extractor (along with a domain discriminator) for each feature group to enable a fine-grained domain adaptation. We design a secure protocol that enables performing the PrADA in a secure and efficient manner. We evaluate our approach on two tabular datasets. Experiments demonstrate both the effectiveness and practicality of our approach.
PDF Published in IEEE Transactions on Big Data
点此查看论文截图
DomainATM: Domain Adaptation Toolbox for Medical Data Analysis
Authors:Hao Guan, Mingxia Liu
Domain adaptation (DA) is an important technique for modern machine learning-based medical data analysis, which aims at reducing distribution differences between different medical datasets. A proper domain adaptation method can significantly enhance the statistical power by pooling data acquired from multiple sites/centers. To this end, we have developed the Domain Adaptation Toolbox for Medical data analysis (DomainATM) - an open-source software package designed for fast facilitation and easy customization of domain adaptation methods for medical data analysis. The DomainATM is implemented in MATLAB with a user-friendly graphical interface, and it consists of a collection of popular data adaptation algorithms that have been extensively applied to medical image analysis and computer vision. With DomainATM, researchers are able to facilitate fast feature-level and image-level adaptation, visualization and performance evaluation of different adaptation methods for medical data analysis. More importantly, the DomainATM enables the users to develop and test their own adaptation methods through scripting, greatly enhancing its utility and extensibility. An overview characteristic and usage of DomainATM is presented and illustrated with three example experiments, demonstrating its effectiveness, simplicity, and flexibility. The software, source code, and manual are available online.
PDF 10 pages, 13 figures
点此查看论文截图
Multiple Modes for Continual Learning
Authors:Siddhartha Datta, Nigel Shadbolt
Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadvertently anchor their updated parameters to a local parameter subspace to remember old tasks, else drift away from the subspace and forget. From this observation, we formulate a trade-off between constructing multiple parameter modes and allocating tasks per mode. Mode-Optimized Task Allocation (MOTA), our contributed adaptation strategy, trains multiple modes in parallel, then optimizes task allocation per mode. We empirically demonstrate improvements over baseline continual learning strategies and across varying distribution shifts, namely sub-population, domain, and task shift.
PDF
点此查看论文截图
Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series
Authors:Sercan O. Arik, Nathanael C. Yoder, Tomas Pfister
Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting — their distributions evolve over time, rendering the conventional training and model selection procedures suboptimal. In this paper, we propose a novel method, Self-Adaptive Forecasting (SAF), to modify the training of time-series forecasting models to improve their performance on forecasting tasks with such non-stationary time-series data. SAF integrates a self-adaptation stage prior to forecasting based on `backcasting’, i.e. predicting masked inputs backward in time. This is a form of test-time training that creates a self-supervised learning problem on test samples before performing the prediction task. In this way, our method enables efficient adaptation of encoded representations to evolving distributions, leading to superior generalization. SAF can be integrated with any canonical encoder-decoder based time-series architecture such as recurrent neural networks or attention-based architectures. On synthetic and real-world datasets in domains where time-series data are known to be notoriously non-stationary, such as healthcare and finance, we demonstrate a significant benefit of SAF in improving forecasting accuracy.
PDF
点此查看论文截图
What Does DALL-E 2 Know About Radiology?
Authors:Lisa C. Adams, Felix Busch, Daniel Truhn, Marcus R. Makowski, Hugo JWL. Aerts, Keno K. Bressem
Generative models such as DALL-E 2 could represent a promising future tool for image generation, augmentation, and manipulation for artificial intelligence research in radiology provided that these models have sufficient medical domain knowledge. Here we show that DALL-E 2 has learned relevant representations of X-ray images with promising capabilities in terms of zero-shot text-to-image generation of new images, continuation of an image beyond its original boundaries, or removal of elements, while pathology generation or CT, MRI, and ultrasound images are still limited. The use of generative models for augmenting and generating radiological data thus seems feasible, even if further fine-tuning and adaptation of these models to the respective domain is required beforehand.
PDF 4 Figures
点此查看论文截图
Stacking Ensemble Learning in Deep Domain Adaptation for Ophthalmic Image Classification
Authors:Yeganeh Madadi, Vahid Seydi, Jian Sun, Edward Chaum, Siamak Yousefi
Domain adaptation is an attractive approach given the availability of a large amount of labeled data with similar properties but different domains. It is effective in image classification tasks where obtaining sufficient label data is challenging. We propose a novel method, named SELDA, for stacking ensemble learning via extending three domain adaptation methods for effectively solving real-world problems. The major assumption is that when base domain adaptation models are combined, we can obtain a more accurate and robust model by exploiting the ability of each of the base models. We extend Maximum Mean Discrepancy (MMD), Low-rank coding, and Correlation Alignment (CORAL) to compute the adaptation loss in three base models. Also, we utilize a two-fully connected layer network as a meta-model to stack the output predictions of these three well-performing domain adaptation models to obtain high accuracy in ophthalmic image classification tasks. The experimental results using Age-Related Eye Disease Study (AREDS) benchmark ophthalmic dataset demonstrate the effectiveness of the proposed model.
PDF
点此查看论文截图
Zero-shot Domain Adaptation for Neural Machine Translation with Retrieved Phrase-level Prompts
Authors:Zewei Sun, Qingnan Jiang, Shujian Huang, Jun Cao, Shanbo Cheng, Mingxuan Wang
Domain adaptation is an important challenge for neural machine translation. However, the traditional fine-tuning solution requires multiple extra training and yields a high cost. In this paper, we propose a non-tuning paradigm, resolving domain adaptation with a prompt-based method. Specifically, we construct a bilingual phrase-level database and retrieve relevant pairs from it as a prompt for the input sentences. By utilizing Retrieved Phrase-level Prompts (RePP), we effectively boost the translation quality. Experiments show that our method improves domain-specific machine translation for 6.2 BLEU scores and improves translation constraints for 11.5% accuracy without additional training.
PDF
点此查看论文截图
Towards Simple and Efficient Task-Adaptive Pre-training for Text Classification
Authors:Arnav Ladkat, Aamir Miyajiwala, Samiksha Jagadale, Rekha Kulkarni, Raviraj Joshi
Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using Domain Adaptive Pre-training (DAPT) and Task-Adaptive Pre-training (TAPT) as an intermediate step before the final finetuning task. This step helps cover the target domain vocabulary and improves the model performance on the downstream task. In this work, we study the impact of training only the embedding layer on the model’s performance during TAPT and task-specific finetuning. Based on our study, we propose a simple approach to make the intermediate step of TAPT for BERT-based models more efficient by performing selective pre-training of BERT layers. We show that training only the BERT embedding layer during TAPT is sufficient to adapt to the vocabulary of the target domain and achieve comparable performance. Our approach is computationally efficient, with 78\% fewer parameters trained during TAPT. The proposed embedding layer finetuning approach can also be an efficient domain adaptation technique.
PDF Accepted at AACL-IJCNLP 2022
点此查看论文截图
Global Weighted Tensor Nuclear Norm for Tensor Robust Principal Component Analysis
Authors:Libin Wang, Yulong Wang, Shiyuan Wang, Youheng Liu, Yutao Hu, Longlong Chen, Hong Chen
Tensor Robust Principal Component Analysis (TRPCA), which aims to recover a low-rank tensor corrupted by sparse noise, has attracted much attention in many real applications. This paper develops a new Global Weighted TRPCA method (GWTRPCA), which is the first approach simultaneously considers the significance of intra-frontal slice and inter-frontal slice singular values in the Fourier domain. Exploiting this global information, GWTRPCA penalizes the larger singular values less and assigns smaller weights to them. Hence, our method can recover the low-tubal-rank components more exactly. Moreover, we propose an effective adaptive weight learning strategy by a Modified Cauchy Estimator (MCE) since the weight setting plays a crucial role in the success of GWTRPCA. To implement the GWTRPCA method, we devise an optimization algorithm using an Alternating Direction Method of Multipliers (ADMM) method. Experiments on real-world datasets validate the effectiveness of our proposed method.
PDF 8 pages
点此查看论文截图
Deep Domain Adaptation for Detecting Bomb Craters in Aerial Images
Authors:Marco Geiger, Dominik Martin, Niklas Kühl
The aftermath of air raids can still be seen for decades after the devastating events. Unexploded ordnance (UXO) is an immense danger to human life and the environment. Through the assessment of wartime images, experts can infer the occurrence of a dud. The current manual analysis process is expensive and time-consuming, thus automated detection of bomb craters by using deep learning is a promising way to improve the UXO disposal process. However, these methods require a large amount of manually labeled training data. This work leverages domain adaptation with moon surface images to address the problem of automated bomb crater detection with deep learning under the constraint of limited training data. This paper contributes to both academia and practice (1) by providing a solution approach for automated bomb crater detection with limited training data and (2) by demonstrating the usability and associated challenges of using synthetic images for domain adaptation.
PDF 56th Annual Hawaii International Conference on System Sciences (HICSS-56)
点此查看论文截图
Open-Ended Diverse Solution Discovery with Regulated Behavior Patterns for Cross-Domain Adaptation
Authors:Kang Xu, Yan Ma, Wei Li, Bingsheng Wei
While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations. Recent works have demonstrated that a policy population with diverse behavior characteristics can generalize to downstream environments with various discrepancies. However, such policies might result in catastrophic damage during the deployment in practical scenarios like real-world systems due to the unrestricted behaviors of trained policies. Furthermore, training diverse policies without regulation of the behavior can result in inadequate feasible policies for extrapolating to a wide range of test conditions with dynamics shifts. In this work, we aim to train diverse policies under the regularization of the behavior patterns. We motivate our paradigm by observing the inverse dynamics in the environment with partial state information and propose Diversity in Regulation(DiR) training diverse policies with regulated behaviors to discover desired patterns that benefit the generalization. Considerable empirical results on various variations of different environments indicate that our method attains improvements over other diversity-driven counterparts.
PDF
点此查看论文截图
Increasing Model Generalizability for Unsupervised Domain Adaptation
Authors:Mohammad Rostami
A dominant approach for addressing unsupervised domain adaptation is to map data points for the source and the target domains into an embedding space which is modeled as the output-space of a shared deep encoder. The encoder is trained to make the embedding space domain-agnostic to make a source-trained classifier generalizable on the target domain. A secondary mechanism to improve UDA performance further is to make the source domain distribution more compact to improve model generalizability. We demonstrate that increasing the interclass margins in the embedding space can help to develop a UDA algorithm with improved performance. We estimate the internally learned multi-modal distribution for the source domain, learned as a result of pretraining, and use it to increase the interclass class separation in the source domain to reduce the effect of domain shift. We demonstrate that using our approach leads to improved model generalizability on four standard benchmark UDA image classification datasets and compares favorably against exiting methods.
PDF Presented 2022 Conference on Lifelong Learning Agents
点此查看论文截图
Unsupervised Domain Adaptation with Histogram-gated Image Translation for Delayered IC Image Analysis
Authors:Yee-Yang Tee, Deruo Cheng, Chye-Soon Chee, Tong Lin, Yiqiong Shi, Bah-Hwee Gwee
Deep learning has achieved great success in the challenging circuit annotation task by employing Convolutional Neural Networks (CNN) for the segmentation of circuit structures. The deep learning approaches require a large amount of manually annotated training data to achieve a good performance, which could cause a degradation in performance if a deep learning model trained on a given dataset is applied to a different dataset. This is commonly known as the domain shift problem for circuit annotation, which stems from the possibly large variations in distribution across different image datasets. The different image datasets could be obtained from different devices or different layers within a single device. To address the domain shift problem, we propose Histogram-gated Image Translation (HGIT), an unsupervised domain adaptation framework which transforms images from a given source dataset to the domain of a target dataset, and utilize the transformed images for training a segmentation network. Specifically, our HGIT performs generative adversarial network (GAN)-based image translation and utilizes histogram statistics for data curation. Experiments were conducted on a single labeled source dataset adapted to three different target datasets (without labels for training) and the segmentation performance was evaluated for each target dataset. We have demonstrated that our method achieves the best performance compared to the reported domain adaptation techniques, and is also reasonably close to the fully supervised benchmark.
PDF 7 pages, 4 figures, To be presented at IEEE PAINE 2022 (oral)
点此查看论文截图