In this paper, we tackle Multi-Source Domain Adaptation (MSDA), a task in transfer learning where one adapts multiple heterogeneous, labeled source probability measures towards a different, unlabeled target measure. We propose a novel framework for MSDA, based on Optimal Transport (OT) and Gaussian Mixture Models (GMMs). Our framework has two key advantages. First, OT between GMMs can be solved efficiently via linear programming. Second, it provides a convenient model for supervised learning, especially classification, as components in the GMM can be associated with existing classes. Based on the GMM-OT problem, we propose a novel technique for calculating barycenters of GMMs. Based on this novel algorithm, we propose two new strategies for MSDA: GMM-Wasserstein Barycenter Transport (WBT) and GMM-Dataset Dictionary Learning (DaDiL). We empirically evaluate our proposed methods on four benchmarks in image classification and fault diagnosis, showing that we improve over the prior art while being faster and involving fewer parameters. Our code is publicly available at https://github.com/eddardd/gmm_msda
Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, we focus on mixture distributions that arise naturally in several application domains where the data contains different sub-populations. For mixture distributions, established distance measures such as the Wasserstein distance do not take into account imbalanced mixture proportions. Thus, even if two mixture distributions have identical mixture components but different mixture proportions, the Wasserstein distance bet…
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models. To address this, parameter-efficient fine-tuning (PEFT) techniques were introduced where small trainable components are injected in the PLM and updated during fine-tuning. We propose AdaMix as a general PEFT method that tunes a mixture of adaptation modules -- given the underlying PEFT method of choice -- introduce…
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models. To address this, parameter-efficient fine-tuning (PEFT) techniques were introduced where small trainable components are injected in the PLM and updated during fine-tuning. We propose AdaMix as a general PEFT method that tunes a mixture of adaptation modules -- given the underlying PEFT method of choice -- introduce…
It has been known for a while that the problem of multi-source domain adaptation can be regarded as a single source domain adaptation task where the source domain corresponds to a mixture of the original source domains. Nonetheless, how to adjust the mixture distribution weights remains an open question. Moreover, most existing work on this topic focuses only on minimizing the error on the source domains and achieving domain-invariant representations, which is insufficient to ensure low error on the target domain. In this work, we present a novel framework that addresses both problems and beat…
In practical machine learning settings, the data on which a model must make predictions often come from a different distribution than the data it was trained on. Here, we investigate the problem of unsupervised multi-source domain adaptation, where a model is trained on labelled data from multiple source domains and must make predictions on a domain for which no labelled data has been seen. Prior work with CNNs and RNNs has demonstrated the benefit of mixture of experts, where the predictions of multiple domain expert classifiers are combined; as well as domain adversarial training, to induce …
University of Concepción（康塞普西翁大学）；Harvard University（哈佛大学）；University of Chile（智利大学）
In this work we address the problem of transferring knowledge obtained from a vast annotated source domain to a low labeled target domain. We propose Adversarial Variational Domain Adaptation (AVDA), a semi-supervised domain adaptation method based on deep variational embedded representations. We use approximate inference and domain adversarial methods to map samples from source and target domains into an aligned class-dependent embedding defined as a Gaussian Mixture Model. AVDA works as a classifier and considers a generative model that helps this classification. We used digits dataset for e…
MoR: Mixture of Ranks for Low-Rank Adaptation Tuning
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Baidu Inc.（百度公司）
Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains. We present a study of various distance-based measures in the context of NLP tasks, that characterize the dissimilarity between domains based on sample estimates. We first conduct analysis experiments to show which of these distance measures can best differentiate samples from same versus different domains, and are correlated with empirical results. Next, we develop a DistanceNet model which uses these dist…
This paper proposes a new method to combine several densities such that each density dominates a separate part of a joint distribution. The method is fully unsupervised, i.e. the parameters in the densities and the thresholds are simultaneously estimated. The approach uses cdf functions in the mixing. This makes it easy to estimate parameters and the resulting density is smooth. Our method may be used both when the tails are heavier and lighter than the rest of the distribution. The presented model is compared with other published models and a very simple model using a univariate transformatio…
OMoE: Diversifying Mixture of Low-Rank Adaptation by Orthogonal Finetuning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（复杂系统认知与决策智能重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
We study location-scale mixture priors for nonparametric statistical problems, including multivariate regression, density estimation and classification. We show that a rate-adaptive procedure can be obtained if the prior is properly constructed. In particular, we show that adaptation is achieved if a kernel mixture prior on a regression function is constructed using a Gaussian kernel, an inverse gamma bandwidth, and Gaussian mixing weights.
Unsupervised domain adaptation (UDA) aims at exploiting related but different data sources to tackle a common task in a target domain. UDA remains a central yet challenging problem in machine learning. In this paper, we present an approach tailored to moderate-dimensional tabular problems which are hugely important in industrial applications and less well-served by the plethora of methods designed for image and language data. Knothe-Rosenblatt Domain Adaptation (KRDA) is based on the Knothe-Rosenblatt transport: we exploit autoregressive density estimation algorithms to accurately model the di…
Learning from Demonstration (LfD) approaches empower end-users to teach robots novel tasks via demonstrations of the desired behaviors, democratizing access to robotics. A key challenge in LfD research is that users tend to provide heterogeneous demonstrations for the same task due to various strategies and preferences. Therefore, it is essential to develop LfD algorithms that ensure \textit{flexibility} (the robot adapts to personalized strategies), \textit{efficiency} (the robot achieves sample-efficient adaptation), and \textit{scalability} (robot reuses a concise set of strategies to repre…
Doremir Music Research AB（多雷米尔音乐研究公司）；Queen Mary University of London（伦敦玛丽女王大学）
This paper addresses the problem of domain adaptation for the task of music source separation. Using datasets from two different domains, we compare the performance of a deep learning-based harmonic-percussive source separation model under different training scenarios, including supervised joint training using data from both domains and pre-training in one domain with fine-tuning in another. We propose an adversarial unsupervised domain adaptation approach suitable for the case where no labelled data (ground-truth source signals) from a target domain is available. By leveraging unlabelled data…
Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts
Yale university（耶鲁大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Hong Kong University of Science（香港科学大学）；Xi’an Jiaotong University（西安交通大学）；Central University of Finance（中央财经大学）
National University of Singapore（新加坡国立大学）；Beijing Institute of Technology（北京理工大学）；Zhejing University（浙江大学）
Deep learning models usually require a large amount of labeled data to achieve satisfactory performance. In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a label scarce target domain, thus potentially alleviates the annotation requirement for deep learning models. However, we find that contemporary domain adaptation methods for cross-domain image understanding perform poorly when source domain is noisy. Weakly Supervised Domain Adaptation (WSDA) studies the domain adaptation problem under the scenario where sour…
Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
The University of Hong Kong（香港大学）；Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；Huawei Cloud Computing Technologies（华为云计算技术）；Ola Dimensions；HKU Shanghai Intelligent Computing Research Center（香港大学上海智能计算研究中心）
In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from synthetic mixtures created by adding up isolated ground-truth sources. Reliance on this synthetic training data is problematic because good performance depends upon the degree of match between the training data and real-world audio, especially in terms of the acoustic conditions and distribution of sources. The acoustic properties can be challenging to accurately…
Theory-inspired Label Shift Adaptation via Aligned Distribution Mixture
College of Science, National University of Defense Technology（国防科技大学理学院）；Institute of Big Data Science and Industry, Shanxi University（山西大学大数据科学与产业研究院）
Stanford University（斯坦福大学）；Courant Institute（柯朗研究所）；Google（谷歌）；New York University（纽约大学）
This work includes a number of novel contributions for the multiple-source adaptation problem. We present new normalized solutions with strong theoretical guarantees for the cross-entropy loss and other similar losses. We also provide new guarantees that hold in the case where the conditional probabilities for the source domains are distinct. Moreover, we give new algorithms for determining the distribution-weighted combination solution for the cross-entropy loss and other losses. We report the results of a series of experiments with real-world datasets. We find that our algorithm outperforms …
