Transfer learning considers a learning process where a new task is solved by transferring relevant knowledge from known solutions to related tasks. While this has been studied experimentally, there lacks a foundational description of the transfer learning problem that exposes what related tasks are, and how they can be exploited. In this work, we present a definition for relatedness between tasks and identify foliations as a mathematical framework to represent such relationships.
Imperial College London（帝国理工学院）；University College London（伦敦大学学院）；University of Sheffield（谢菲尔德大学）
Learning to transfer considers learning solutions to tasks in a such way that relevant knowledge can be transferred from known task solutions to new, related tasks. This is important for general learning, as well as for improving the efficiency of the learning process. While techniques for learning to transfer have been studied experimentally, we still lack a foundational description of the problem that exposes what related tasks are, and how relationships between tasks can be exploited constructively. In this work, we introduce a framework using the differential geometric theory of foliations…
Sichuan University（四川大学）；Harbin Engineering University（哈尔滨工程大学）；University of Electronic Science and Technology of China（电子科技大学）；New York University（纽约大学）；University of California, Berkeley（加州大学伯克利分校）
Time Series Classification (TSC) has been an important and challenging task in data mining, especially on multivariate time series and multi-view time series data sets. Meanwhile, transfer learning has been widely applied in computer vision and natural language processing applications to improve deep neural network's generalization capabilities. However, very few previous works applied transfer learning framework to time series mining problems. Particularly, the technique of measuring similarities between source domain and target domain based on dynamic representation such as density estimatio…
Intelligent recommendation technology has been playing an increasingly important role in various industry applications such as e-commerce product promotion and Internet advertisement display. Besides users' feedbacks (e.g., numerical ratings) on items as usually exploited by some typical recommendation algorithms, there are often some additional data such as users' social circles and other behaviors. Such auxiliary data are usually related to users' preferences on items behind the numerical ratings. Collaborative recommendation with auxiliary data (CRAD) aims to leverage such additional inform…
Improving automatic endoscopic stone recognition using a multi-view fusion approach enhanced with two-step transfer learning
Tecnologico de Monterrey, School of Engineering and Sciences, Mexico（墨西哥蒙特雷科技大学工程与科学学院）；CRAN UMR 7039, Université de Lorraine and CNRS, Nancy, France（法国洛林大学CNRS CRAN UMR 7039研究中心）；CINVESTAV, Guadalajara, Mexico（墨西哥瓜达拉哈拉科学技术研究所）；CHRU Nancy, Service d’urologie de Brabois, Nancy, France（法国南锡布拉布瓦大学医院泌尿外科）
A Novel TSK Fuzzy System Incorporating Multi-view Collaborative Transfer Learning for Personalized Epileptic EEG Detection
School of Artificial Intelligence and Computer Science, Jiangnan University and Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education（江南大学人工智能与计算机科学学院，智能医疗技术工程研究中心，教育部）；School of Computer and Information Engineering, Institute for Artificial Intelligence, Shanghai Polytechnic University（上海理工大学计算机与信息工程学院，人工智能研究院）；School of Internet of Things Engineering, Wuxi University（无锡大学物联网工程学院）
MVKTrans: Multi-View Knowledge Transfer for Robust Multiomics Classification
College of Intelligent Systems Science and Engineering, Harbin Engineering University（哈尔滨工程大学智能系统科学与工程学院）；Qingdao Innovation and Development Center, Harbin Engineering University（哈尔滨工程大学青岛创新发展中心）；Institute of Medical Information, Chinese Academy of Medical Sciences & Peking Union Medical College（中国医学科学院北京协和医学院医学信息研究所）
Siemens AG（西门子股份公司）；University of Munich (LMU)（慕尼黑大学（LMU））
Though word embeddings and topics are complementary representations, several past works have only used pre-trained word embeddings in (neural) topic modeling to address data sparsity problem in short text or small collection of documents. However, no prior work has employed (pre-trained latent) topics in transfer learning paradigm. In this paper, we propose an approach to (1) perform knowledge transfer using latent topics obtained from a large source corpus, and (2) jointly transfer knowledge via the two representations (or views) in neural topic modeling to improve topic quality, better deal …
Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加州大学）；UC San Diego（加利福尼亚大学圣地亚哥分校）
Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the model size and the number of tasks grow. Recent work has proposed a variety of parameter-efficient transfer learning methods that only fine-tune a small number of (extra) parameters to attain strong performance. While effective, the critical ingredients for success and the connections among the various methods are poorly understood. In this paper, we break down…
Beijing National Research Center for Information Science and Technology (BNRist)（北京国家信息科学与技术研究中心（BNRist））；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）
Helsinki Institute for Information Technology HIIT（赫尔辛基信息技术研究所（HIIT））；Aalto University（阿尔托大学）；Aix-Marseille University（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；Turing Center for Living Systems (CENTURI)（图灵生命系统中心（CENTURI））
We consider the kernel completion problem with the presence of multiple views in the data. In this context the data samples can be fully missing in some views, creating missing columns and rows to the kernel matrices that are calculated individually for each view. We propose to solve the problem of completing the kernel matrices with Cross-View Kernel Transfer (CVKT) procedure, in which the features of the other views are transformed to represent the view under consideration. The transformations are learned with kernel alignment to the known part of the kernel matrix, allowing for finding gene…
Bayesian optimization (BO) is a successful methodology to optimize black-box functions that are expensive to evaluate. While traditional methods optimize each black-box function in isolation, there has been recent interest in speeding up BO by transferring knowledge across multiple related black-box functions. In this work, we introduce a method to automatically design the BO search space by relying on evaluations of previous black-box functions. We depart from the common practice of defining a set of arbitrary search ranges a priori by considering search space geometries that are learned from…
In this paper, we consider the problem of multi-view clustering on incomplete views. Compared with complete multi-view clustering, the view-missing problem increases the difficulty of learning common representations from different views. To address the challenge, we propose a novel incomplete multi-view clustering framework, which incorporates cross-view relation transfer and multi-view fusion learning. Specifically, based on the consistency existing in multi-view data, we devise a cross-view relation transfer-based completion module, which transfers known similar inter-instance relationships …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Machine learning (ML) robustness and domain generalization are fundamentally correlated: they essentially concern data distribution shifts under adversarial and natural settings, respectively. On one hand, recent studies show that more robust (adversarially trained) models are more generalizable. On the other hand, there is a lack of theoretical understanding of their fundamental connections. In this paper, we explore the relationship between regularization and domain transferability considering different factors such as norm regularization and data augmentations (DA). We propose a general the…
The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL). Street View can be a sensible testbed for such RL agents, because it provides real-world photographic imagery at ground level, with diverse street appearances; it has been made into an interactive environment called StreetLearn and used for research on navigation. However, goal-driven street navigation agents have not so far been able to transfer to unseen areas without extensive retraining, and relying on simulatio…
Recent deep learning models have achieved high performance in speech enhancement; however, it is still challenging to obtain a fast and low-complexity model without significant performance degradation. Previous knowledge distillation studies on speech enhancement could not solve this problem because their output distillation methods do not fit the speech enhancement task in some aspects. In this study, we propose multi-view attention transfer (MV-AT), a feature-based distillation, to obtain efficient speech enhancement models in the time domain. Based on the multi-view features extraction mode…
Bryn Mawr College（布林莫尔学院）；University of Maryland, Baltimore County（马里兰大学巴尔的摩分校）；Lockheed Martin Advanced Technology Laboratories（洛克希德·马丁先进技术实验室）
Multi-view learning algorithms typically assume a complete bipartite mapping between the different views in order to exchange information during the learning process. However, many applications provide only a partial mapping between the views, creating a challenge for current methods. To address this problem, we propose a multi-view algorithm based on constrained clustering that can operate with an incomplete mapping. Given a set of pairwise constraints in each view, our approach propagates these constraints using a local similarity measure to those instances that can be mapped to the other vi…
ShanghaiTech University（上海科技大学）；Tencent AI Lab（腾讯人工智能实验室）
We tackle the human motion imitation, appearance transfer, and novel view synthesis within a unified framework, which means that the model once being trained can be used to handle all these tasks. The existing task-specific methods mainly use 2D keypoints (pose) to estimate the human body structure. However, they only expresses the position information with no abilities to characterize the personalized shape of the individual person and model the limbs rotations. In this paper, we propose to use a 3D body mesh recovery module to disentangle the pose and shape, which can not only model the join…
University of Birmingham（伯明翰大学）；Poznan University of Technology（波兹南工业大学）
This paper concerns the problem of how to learn to grasp dexterously, so as to be able to then grasp novel objects seen only from a single view-point. Recently, progress has been made in data-efficient learning of generative grasp models which transfer well to novel objects. These generative grasp models are learned from demonstration (LfD). One weakness is that, as this paper shall show, grasp transfer under challenging single view conditions is unreliable. Second, the number of generative model elements rises linearly in the number of training examples. This, in turn, limits the potential of…
