Recent metric-based meta-learning approaches, which learn a metric space that generalizes well over combinatorial number of different classification tasks sampled from a task distribution, have been shown to be effective for few-shot classification tasks of unseen classes. They are often trained with episodic training where they iteratively train a common metric space that reduces distance between the class representatives and instances belonging to each class, over large number of episodes with random classes. However, this training is limited in that while the main target is the generalization to the classification of unseen classes during training, there is no explicit consideration of generalization during meta-training phase. To tackle this issue, we propose a simple yet effective meta-learning framework for metricbased approaches, which we refer to as learning to generalize (L2G), that explicitly constrains the learning on a sampled classification task to reduce the classification error on a randomly sampled unseen classification task with a bilevel optimization scheme. This explicit learning aimed toward generalization allows the model to obtain a metric that separates well between unseen classes. We validate our L2G framework on mini-ImageNet and tiered-ImageNet datasets with two base meta-learning few-shot classification models, Prototypical Networks and Relation Networks. The results show that L2G significantly improves the performance of the two methods over episodic training. Further visualization shows that L2G obtains a metric space that clusters and separates unseen classes well.
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）
Learning to classify unseen class samples at test time is popularly referred to as zero-shot learning (ZSL). If test samples can be from training (seen) as well as unseen classes, it is a more challenging problem due to the existence of strong bias towards seen classes. This problem is generally known as \emph{generalized} zero-shot learning (GZSL). Thanks to the recent advances in generative models such as VAEs and GANs, sample synthesis based approaches have gained considerable attention for solving this problem. These approaches are able to handle the problem of class bias by synthesizing u…
Learning to Generalize Unseen Domains via Multi-Source Meta Learning for Text Classification
Shenzhen MSU-BIT University（深圳北理莫斯科大学）；Sun Yat-Sen University（中山大学）；SIAT, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing（粤港澳情感智能与普适计算联合实验室）
Meta-learning provides a promising way for learning to efficiently learn and achieves great success in many applications. However, most meta-learning literature focuses on dealing with tasks from a same domain, making it brittle to generalize to tasks from the other unseen domains. In this work, we address this problem by simulating tasks from the other unseen domains to improve the generalization and robustness of meta-learning method. Specifically, we propose a model-agnostic shift layer to learn how to simulate the domain shift and generate pseudo tasks, and develop a new adversarial learni…
Rensselaer Polytechnic Institute（伦斯勒理工学院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Stochastic bilevel optimization generalizes the classic stochastic optimization from the minimization of a single objective to the minimization of an objective function that depends the solution of another optimization problem. Recently, stochastic bilevel optimization is regaining popularity in emerging machine learning applications such as hyper-parameter optimization and model-agnostic meta learning. To solve this class of stochastic optimization problems, existing methods require either double-loop or two-timescale updates, which are sometimes less efficient. This paper develops a new opti…
University of Amsterdam（阿姆斯特丹大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）；National Center for Artificial Intelligence, Saudi Data and Artificial Intelligence Authority（沙特数据与人工智能局国家人工智能中心）
We strive to learn a model from a set of source domains that generalizes well to unseen target domains. The main challenge in such a domain generalization scenario is the unavailability of any target domain data during training, resulting in the learned model not being explicitly adapted to the unseen target domains. We propose learning to generalize across domains on single test samples. We leverage a meta-learning paradigm to learn our model to acquire the ability of adaptation with single samples at training time so as to further adapt itself to each single test sample at test time. We form…
Deep learning models perform best when tested on target (test) data domains whose distribution is similar to the set of source (train) domains. However, model generalization can be hindered when there is significant difference in the underlying statistics between the target and source domains. In this work, we adapt a domain generalization method based on a model-agnostic meta-learning framework to biomedical imaging. The method learns a domain-agnostic feature representation to improve generalization of models to the unseen test distribution. The method can be used for any imaging task, as it…
A common problem with most zero and few-shot learning approaches is they suffer from bias towards seen classes resulting in sub-optimal performance. Existing efforts aim to utilize unlabeled images from unseen classes (i.e transductive zero-shot) during training to enable generalization. However, this limits their use in practical scenarios where data from target unseen classes is unavailable or infeasible to collect. In this work, we present a practical setting of inductive zero and few-shot learning, where unlabeled images from other out-of-data classes, that do not belong to seen or unseen …
Spatial autocorrelation and spatial heterogeneity widely exist in spatial data, which make the traditional machine learning model perform badly. Spatial domain generalization is a spatial extension of domain generalization, which can generalize to unseen spatial domains in continuous 2D space. Specifically, it learns a model under varying data distributions that generalizes to unseen domains. Although tremendous success has been achieved in domain generalization, there exist very few works on spatial domain generalization. The advancement of this area is challenged by: 1) Difficulty in charact…
Microsoft Research Asia（微软亚洲研究院）；School of Data Science, Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Institute for Data Science, Tsinghua University（清华大学数据科学研究院）
Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years. Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain. Great progress has been made in the area of domain generalization for years. This p…
From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation
Huawei Noah’s Ark Lab（华为诺亚实验室）；Department of Data Science, EURECOM（EURECOM数据科学系）；Cognizant AI Lab（Cognizant人工智能实验室）；Statistics Program, KAUST（KAUST统计学项目）
Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation
School of Software Engineering, Dalian University of Technology（大连理工大学软件学院）；CRRC Qingdao Sifang Rolling Stock Research Institute Co., Ltd（中车青岛四方机车车辆股份有限公司）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））
Graph4BiLO: Graph Neural Network Approximation for Bilevel Mixed-Integer Linear Optimization
Bellini College of Artificial Intelligence, Cybersecurity and Computing, University of South Florida（南佛罗里达大学贝利尼人工智能、网络安全与计算学院）；Muma College of Business, University of South Florida（南佛罗里达大学穆玛商学院）；University of South Florida（南佛罗里达大学）
George Mason University（乔治梅森大学）；Argonne National Laboratory（阿贡国家实验室）
In this work we consider a generalized bilevel optimization framework for solving inverse problems. We introduce fractional Laplacian as a regularizer to improve the reconstruction quality, and compare it with the total variation regularization. We emphasize that the key advantage of using fractional Laplacian as a regularizer is that it leads to a linear operator, as opposed to the total variation regularization which results in a nonlinear degenerate operator. Inspired by residual neural networks, to learn the optimal strength of regularization and the exponent of fractional Laplacian, we de…
CEA LIST（法国原子能委员会列表实验室）；CEDRIC Lab – CNAM（法国国立工艺学院CEDRIC实验室）
Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes. It relies on additional semantic knowledge for which a mapping can be learned with training examples of seen classes. While classical ZSL considers the recognition performance on unseen classes only, generalized zero-shot learning (GZSL) aims at maximizing performance on both seen and unseen classes. In this paper, we propose a new process for training and evaluation in the GZSL setting; this process addresses the gap in performance between samples from unseen and seen classes by penalizing the latter, and…
Machine Learning-Augmented Optimization of Large Bilevel and Two-stage Stochastic Programs: Application to Cycling Network Design
Department of Mechanical & Industrial Engineering, University of Toronto（机械与工业工程系，多伦多大学）；Department of Civil & Mineral Engineering, University of Toronto（土木与矿物工程系，多伦多大学）
East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）；Tecent（腾讯）
Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen classes are available. However, such an assumption is unrealistic when new unseen classes appear dynamically. To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural netw…
Typical amortized inference in variational autoencoders is specialized for a single probabilistic query. Here we propose an inference network architecture that generalizes to unseen probabilistic queries. Instead of an encoder-decoder pair, we can train a single inference network directly from data, using a cost function that is stochastic not only over samples, but also over queries. We can use this network to perform the same inference tasks as we would in an undirected graphical model with hidden variables, without having to deal with the intractable partition function. The results can be m…
Random Features Hopfield Networks generalize retrieval to previously unseen examples
University of Rome ‘La Sapienza’（罗马第一大学）；Harvard University（哈佛大学）；Bocconi University（博科尼大学）；Institute for Data Science and Analytics（数据科学与分析研究所）；CNR-NANOTEC, Institute of Nanotechnology（国家研究委员会纳米技术研究所（CNR-NANOTEC））
Generalized zero-shot learning (GZSL) aims at training a model that can generalize to unseen class data by only using auxiliary information. One of the main challenges in GZSL is a biased model prediction toward seen classes caused by overfitting on only available seen class data during training. To overcome this issue, we propose a two-stream autoencoder-based gating model for GZSL. Our gating model predicts whether the query data is from seen classes or unseen classes, and utilizes separate seen and unseen experts to predict the class independently from each other. This framework avoids comp…
A well trained and generalized deep neural network (DNN) should be robust to both seen and unseen classes. However, the performance of most of the existing supervised DNN algorithms degrade for classes which are unseen in the training set. To learn a discriminative classifier which yields good performance in Zero-Shot Learning (ZSL) settings, we propose to generate an Over-Complete Distribution (OCD) using Conditional Variational Autoencoder (CVAE) of both seen and unseen classes. In order to enforce the separability between classes and reduce the class scatter, we propose the use of Online Ba…
National Tsing Hua University（台湾清华大学）；Google AI Research（谷歌人工智能研究院）；Appier Inc.（沛星互动科技股份有限公司）
Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can grow or an environment sometimes needs to interact with a changing number of agents in real-world scenarios. To this end, a multi-agent framework needs to handle various scenarios of agents, in terms of both scales and dynamics, for being practical to real-world applications. We formulate the multi-agent environment with a different number of agents as a multi-tasking problem and propose a meta reinforcement learning…
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in the graph are present during training of the embeddings; these previous approaches are inherently transductive and do not naturally generalize to unseen nodes. Here we present GraphSAGE, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data. Instead of tr…
We show that Reinforcement Learning (RL) methods for solving Text-Based Games (TBGs) often fail to generalize on unseen games, especially in small data regimes. To address this issue, we propose Context Relevant Episodic State Truncation (CREST) for irrelevant token removal in observation text for improved generalization. Our method first trains a base model using Q-learning, which typically overfits the training games. The base model's action token distribution is used to perform observation pruning that removes irrelevant tokens. A second bootstrapped model is then retrained on the pruned ob…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；University of Tübingen（图宾根大学）
Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations. Our confidence-calibrated adversarial training (CCAT) tackles this problem by biasing the model towards low confidence predictions on adversarial examples. By allowing to reject examples with low confidence, robustness generalizes beyond the threat model employed during training. CCAT, trained only on $L_\infty$ adversarial examples, increases robustness ag…
The University of Queensland（昆士兰大学）；University of Electronic Science and Technology of China（电子科技大学）
Generalized Zero-Shot Learning (GZSL) aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. However, due to the generation shifts, the synthesized samples by most existing methods may drift from the real distribution of the unseen data. To address this issue, we propose a novel flow-based generative framework that consists of multiple conditional affine couplin…
Our goal is to generate a policy to complete an unseen task given just a single video demonstration of the task in a given domain. We hypothesize that to successfully generalize to unseen complex tasks from a single video demonstration, it is necessary to explicitly incorporate the compositional structure of the tasks into the model. To this end, we propose Neural Task Graph (NTG) Networks, which use conjugate task graph as the intermediate representation to modularize both the video demonstration and the derived policy. We empirically show NTG achieves inter-task generalization on two complex…
Simulation of the dynamics of physical systems is essential to the development of both science and engineering. Recently there is an increasing interest in learning to simulate the dynamics of physical systems using neural networks. However, existing approaches fail to generalize to physical substances not in the training set, such as liquids with different viscosities or elastomers with different elasticities. Here we present a machine learning method embedded with physical priors and material parameters, which we term as "Graph-based Physics Engine" (GPE), to efficiently model the physical d…
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
University of Maryland, College Park（马里兰大学学院公园分校）；University of Central Florida（中佛罗里达大学）；J.P. Morgan AI Research（摩根大通人工智能研究院）；Oregon State University（俄勒冈州立大学）；Princeton University（普林斯顿大学）
Zero-shot learning (ZSL) addresses the unseen class recognition problem by leveraging semantic information to transfer knowledge from seen classes to unseen classes. Generative models synthesize the unseen visual features and convert ZSL into a classical supervised learning problem. These generative models are trained using the seen classes and are expected to implicitly transfer the knowledge from seen to unseen classes. However, their performance is stymied by overfitting, which leads to substandard performance on Generalized Zero-Shot learning (GZSL). To address this concern, we propose the…
The growth of cross-lingual pre-trained models has enabled NLP tools to rapidly generalize to new languages. While these models have been applied to tasks involving entities, their ability to explicitly predict typological features of these entities across languages has not been established. In this paper, we present a unified cross-lingual fine-grained entity typing model capable of handling over 100 languages and analyze this model's ability to generalize to languages and entities unseen during training. We train this model on cross-lingual training data collected from Wikipedia hyperlinks i…
University of Technology Sydney（悉尼科技大学）；University of Washington（华盛顿大学）
Zero-shot learning (ZSL) aims to classify images of an unseen class only based on a few attributes describing that class but no access to any training sample. A popular strategy is to learn a mapping between the semantic space of class attributes and the visual space of images based on the seen classes and their data. Thus, an unseen class image can be ideally mapped to its corresponding class attributes. The key challenge is how to align the representations in the two spaces. For most ZSL settings, the attributes for each seen/unseen class are only represented by a vector while the seen-class…
Zero-Shot Learning (ZSL) is a classification task where we do not have even a single training labeled example from a set of unseen classes. Instead, we only have prior information (or description) about seen and unseen classes, often in the form of physically realizable or descriptive attributes. Lack of any single training example from a set of classes prohibits use of standard classification techniques and losses, including the popular crossentropy loss. Currently, state-of-the-art approaches encode the prior class information into dense vectors and optimize some distance between the learned…
