We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by exploiting stable patterns in loss surfaces. Our method implicitly estimates the gradients of a scaled loss function while retaining the general properties intact for parameter updates. Besides providing improved performance on few-shot tasks, our framework could be easily extended to do network architecture search. We further propose a novel dual encoder, affinity-score based decoder topology that achieves additional improvements to performance. Experiments on an internal dataset, MQ2007, and AwA2 show our approach outperforms existing alternative approaches by 21%, 8%, and 4% respectively on accuracy and NDCG metrics. On Mini-ImageNet dataset our approach achieves comparable results with Prototypical Networks. Empirical evaluations demonstrate that our approach provides a unified and effective framework.
Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA's vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain …
University of Michigan（密歇根大学）；Google Brain（谷歌大脑）；Microsoft Research（微软研究院）
As a step towards developing zero-shot task generalization capabilities in reinforcement learning (RL), we introduce a new RL problem where the agent should learn to execute sequences of instructions after learning useful skills that solve subtasks. In this problem, we consider two types of generalizations: to previously unseen instructions and to longer sequences of instructions. For generalization over unseen instructions, we propose a new objective which encourages learning correspondences between similar subtasks by making analogies. For generalization over sequential instructions, we pres…
Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depends on the tasks available for meta-training: in the same way that supervised learning generalizes best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In…
Microsoft AI & Research（微软人工智能与研究）；IBM Research AI（IBM研究人工智能）；JD AI Research（京东人工智能研究）
Few-shot Learning aims to learn classifiers for new classes with only a few training examples per class. Existing meta-learning or metric-learning based few-shot learning approaches are limited in handling diverse domains with various number of labels. The meta-learning approaches train a meta learner to predict weights of homogeneous-structured task-specific networks, requiring a uniform number of classes across tasks. The metric-learning approaches learn one task-invariant metric for all the tasks, and they fail if the tasks diverge. We propose to deal with these limitations with meta metric…
McGill University（麦吉尔大学）；Quebec AI Institute（魁北克人工智能研究所）；UC Berkeley（加州大学伯克利分校）；Google Brain（谷歌大脑）
Reinforcement learning (RL) agents are widely used for solving complex sequential decision making tasks, but still exhibit difficulty in generalizing to scenarios not seen during training. While prior online approaches demonstrated that using additional signals beyond the reward function can lead to better generalization capabilities in RL agents, i.e. using self-supervised learning (SSL), they struggle in the offline RL setting, i.e. learning from a static dataset. We show that performance of online algorithms for generalization in RL can be hindered in the offline setting due to poor estimat…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；NVIDIA（英伟达）
Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks during meta-training to quickly adapt to new tasks during meta-testing. In this formulation, the number of shots exploited during meta-training has an impact on the recognition performance at meta-test time. Generally, the shot number used in meta-training should match the one us…
University College London（伦敦大学学院）；University of California, Berkeley（加州大学伯克利分校）；Meta AI Research（Meta人工智能研究院）
The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to produce RL algorithms whose policies generalise well to novel unseen situations at deployment time, avoiding overfitting to their training environments. Tackling this is vital if we are to deploy reinforcement learning algorithms in real world scenarios, where the environment will be diverse, dynamic and unpredictable. This survey is an overview of this nascent field. We rely on a unifying formalism and terminology for discussing different ZSG problems, building upon previous works. We go on to categorise e…
University of Michigan（密歇根大学）；DeepMind（深度思考）；Google Brain（谷歌大脑）
We introduce a new RL problem where the agent is required to generalize to a previously-unseen environment characterized by a subtask graph which describes a set of subtasks and their dependencies. Unlike existing hierarchical multitask RL approaches that explicitly describe what the agent should do at a high level, our problem only describes properties of subtasks and relationships among them, which requires the agent to perform complex reasoning to find the optimal subtask to execute. To solve this problem, we propose a neural subtask graph solver (NSGS) which encodes the subtask graph using…
We present a new deep meta reinforcement learner, which we call Deep Episodic Value Iteration (DEVI). DEVI uses a deep neural network to learn a similarity metric for a non-parametric model-based reinforcement learning algorithm. Our model is trained end-to-end via back-propagation. Despite being trained using the model-free Q-learning objective, we show that DEVI's model-based internal structure provides `one-shot' transfer to changes in reward and transition structure, even for tasks with very high-dimensional state spaces.
The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
ABV-Indian Institute of Information Technology and Management, Gwalior（ABV印度信息技术与管理学院（瓜廖尔））
Robotics has proved to be an indispensable tool in many industrial as well as social applications, such as warehouse automation, manufacturing, disaster robotics, etc. In most of these scenarios, damage to the agent while accomplishing mission-critical tasks can result in failure. To enable robotic adaptation in such situations, the agent needs to adopt policies which are robust to a diverse set of damages and must do so with minimum computational complexity. We thus propose a damage aware control architecture which diagnoses the damage prior to gait selection while also incorporating domain r…
University of Electronic Science and Technology of China（中国电子科技大学）；University of Maryland, College Park（马里兰大学帕克分校）；Iowa State University（爱荷华州立大学）
Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning …
Stevens Institute of Technology（斯蒂文斯理工学院）；Massachusetts Institute of Technology（麻省理工学院）；Wing, Alphabet Inc.（Alphabet公司Wing部门）
This paper studies the problem of autonomous exploration under localization uncertainty for a mobile robot with 3D range sensing. We present a framework for self-learning a high-performance exploration policy in a single simulation environment, and transferring it to other environments, which may be physical or virtual. Recent work in transfer learning achieves encouraging performance by domain adaptation and domain randomization to expose an agent to scenarios that fill the inherent gaps in sim2sim and sim2real approaches. However, it is inefficient to train an agent in environments with rand…
Many real-world problems are compositional - solving them requires completing interdependent sub-tasks, either in series or in parallel, that can be represented as a dependency graph. Deep reinforcement learning (RL) agents often struggle to learn such complex tasks due to the long time horizons and sparse rewards. To address this problem, we present Compositional Design of Environments (CoDE), which trains a Generator agent to automatically build a series of compositional tasks tailored to the RL agent's current skill level. This automatic curriculum not only enables the agent to learn more c…
Tsinghua University（清华大学）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；KIRC, Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院知识图谱与推理中心（KIRC））；Beijing National Research Center for Information Science and Technology（北京国家信息科学与技术研究中心）
Multi-hop knowledge graph (KG) reasoning is an effective and explainable method for predicting the target entity via reasoning paths in query answering (QA) task. Most previous methods assume that every relation in KGs has enough training triples, regardless of those few-shot relations which cannot provide sufficient triples for training robust reasoning models. In fact, the performance of existing multi-hop reasoning methods drops significantly on few-shot relations. In this paper, we propose a meta-based multi-hop reasoning method (Meta-KGR), which adopts meta-learning to learn effective met…
The Swiss AI Lab IDSIA（瑞士人工智能实验室IDSIA）；USI（瑞士意大利语区大学）；SUPSI（瑞士南方应用科技大学）
Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function that decides how future individuals will learn. Unlike recent meta-RL algorithms, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training. In some cases, it even outperforms human-engineered RL algorithms. MetaGenRL uses off-policy…
Lanzhou University of Technology（兰州理工大学）；University College London（伦敦大学学院）；Beijing University of Posts and Telecommunications（北京邮电大学）
Few-shot meta-learning has been recently reviving with expectations to mimic humanity's fast adaption to new concepts based on prior knowledge. In this short communication, we give a concise review on recent representative methods in few-shot meta-learning, which are categorized into four branches according to their technical characteristics. We conclude this review with some vital current challenges and future prospects in few-shot meta-learning.
NTT Computer and Data Science Laboratories, NTT Corporation（NTT公司NTT计算机与数据科学实验室）；Kyoto University（京都大学）
Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized NNs can easily overfit to such small dataset. Previous work (e.g. MAML by Finn et al. 2017) tackles this challenge by meta-learning, which learns how to learn from a few data by using various tasks. On the other hand, one conventional approach to avoid overfitting is restricting hypothesis spaces by endowing sparse NN structures like convolution layers in computer vision. However, although such manually-designed spar…
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Freiburg（弗莱堡大学）
The recent progress in neural architecture search (NAS) has allowed scaling the automated design of neural architectures to real-world domains, such as object detection and semantic segmentation. However, one prerequisite for the application of NAS are large amounts of labeled data and compute resources. This renders its application challenging in few-shot learning scenarios, where many related tasks need to be learned, each with limited amounts of data and compute time. Thus, few-shot learning is typically done with a fixed neural architecture. To improve upon this, we propose MetaNAS, the fi…
University of Michigan（密歇根大学）；LG AI Research Center（LG人工智能研究中心）；Google Research（谷歌研究院）
We tackle real-world problems with complex structures beyond the pixel-based game or simulator. We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph that defines a set of subtasks and their dependencies that are unknown to the agent. Different from the previous meta-rl methods trying to directly infer the unstructured task embedding, our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks, and use it as a prior to improve the task inference in…
Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial examples. The goal of our work is to produce networks which both perform well at few-shot classification tasks and are simultaneously robust to adversarial examples. We develop an algorithm, called Adversarial Querying (AQ), for producing adversarially robust meta-learners, and we thoroughly investigate the causes for adversarial vulnerability. Moreover, ou…
Few-shot meta-learning methods consider the problem of learning new tasks from a small, fixed number of examples, by meta-learning across static data from a set of previous tasks. However, in many real world settings, it is more natural to view the problem as one of minimizing the total amount of supervision --- both the number of examples needed to learn a new task and the amount of data needed for meta-learning. Such a formulation can be studied in a sequential learning setting, where tasks are presented in sequence. When studying meta-learning in this online setting, a critical question ari…
Indian Institute of Technology, Ropar（印度理工学院罗巴尔分校）
Meta-learning (ML) has emerged as a promising learning method under resource constraints such as few-shot learning. ML approaches typically propose a methodology to learn generalizable models. In this work-in-progress paper, we put the recent ML approaches to a stress test to discover their limitations. Precisely, we measure the performance of ML approaches for few-shot learning against increasing task complexity. Our results show a quick degradation in the performance of initialization strategies for ML (MAML, TAML, and MetaSGD), while surprisingly, approaches that use an optimization strateg…
Existing meta-learning based few-shot learning (FSL) methods typically adopt an episodic training strategy whereby each episode contains a meta-task. Across episodes, these tasks are sampled randomly and their relationships are ignored. In this paper, we argue that the inter-meta-task relationships should be exploited and those tasks are sampled strategically to assist in meta-learning. Specifically, we consider the relationships defined over two types of meta-task pairs and propose different strategies to exploit them. (1) Two meta-tasks with disjoint sets of classes: this pair is interesting…
School of Computing and Augmented Intelligence（计算与增强智能学院）；Arizona State University（亚利桑那州立大学）
Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with deep learning to learn a generalizable Q-function for such problems. The learned Q-function can be efficiently transferred to related problems that have different object names and object quantities, and thus, entirely different state spaces. We show that the learned generalized Q-function can be utilized for zero-shot transfer to related problems without an explicit, hand-coded…
University of Technology Sydney（悉尼科技大学）；Western Sydney University（西悉尼大学）；Óbuda University（欧布达大学）
Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (I) metric-based, (II) memory-based, (III), and learning-based methods. Final…
We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data. Compared to other research areas like computer vision, few-shot learning for audio recognition has been under-studied. We formulate few-shot AED problem and explore different ways of utilizing traditional supervised methods for this setting as well as a variety of meta-learning approaches, which are conventionally used to solve few-shot classification problem. Compared to supervised baselines, meta-learning models achieve superior performance, thus s…
Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of meta-learning and the difference between models trained using meta-learning and models which are trained classically. In doing so, we introduce and verify several hypotheses for why meta-learned models perform better. Furthermore, we develop a regularizer which boosts the perfor…
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）；Nanyang Technological University（南洋理工大学）
Meta Reinforcement Learning (MRL) enables an agent to learn from a limited number of past trajectories and extrapolate to a new task. In this paper, we attempt to improve the robustness of MRL. We build upon model-agnostic meta-learning (MAML) and propose a novel method to generate adversarial samples for MRL by using Generative Adversarial Network (GAN). That allows us to enhance the robustness of MRL to adversal attacks by leveraging these attacks during meta training process.
Rice University（莱斯大学）；University of Texas, Austin（德克萨斯大学奥斯汀分校）
We present a new approach, called meta-meta classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of learners, where each learner has high bias and low variance and is skilled at solving a specific type of learning problem. The meta-meta classifier learns how to examine a given learning problem and combine the various learners to solve the problem. The meta-meta learning approach is especially suited to solving few-shot learning tasks, as it is easier to learn to classify a new learning problem with little data tha…
Despite recent advances in its theoretical understanding, there still remains a significant gap in the ability of existing PAC-Bayesian theories on meta-learning to explain performance improvements in the few-shot learning setting, where the number of training examples in the target tasks is severely limited. This gap originates from an assumption in the existing theories which supposes that the number of training examples in the observed tasks and the number of training examples in the target tasks follow the same distribution, an assumption that rarely holds in practice. By relaxing this ass…
KnowPC: Knowledge-Driven Programmatic Reinforcement Learning for Zero-shot Coordination
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（中国科学技术大学认知智能国家重点实验室）；Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
Nanjing University（南京大学）；Ohio State University（俄亥俄州立大学）
Few-shot learning (FSL) aims to generate a classifier using limited labeled examples. Many existing works take the meta-learning approach, constructing a few-shot learner that can learn from few-shot examples to generate a classifier. Typically, the few-shot learner is constructed or meta-trained by sampling multiple few-shot tasks in turn and optimizing the few-shot learner's performance in generating classifiers for those tasks. The performance is measured by how well the resulting classifiers classify the test (i.e., query) examples of those tasks. In this paper, we point out two potential …
University of Virginia（弗吉尼亚大学）；Arizona State University（亚利桑那州立大学）
Few-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i.e., meta-training classes) and then generalize to classes with limited labeled nodes (i.e., meta-test classes). Nevertheless, on real-world graphs, it is usually difficult to obtain abundant labeled nodes for many classes. In practice, each meta-training class can only consist of several labeled nodes, known as the extremely weak supervision problem. In few-shot node classification, with extremel…
Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy
Huazhong University of Science and Technology（华中科技大学）；Nanyang Technological University（南洋理工大学）；University of Washington（华盛顿大学）；University of Copenhagen（哥本哈根大学）
School of Computing Science（计算机科学学院）；Simon Fraser University（西蒙弗雷泽大学）
The goal of few-shot classification is to learn a model that can classify novel classes using only a few training examples. Despite the promising results shown by existing meta-learning algorithms in solving the few-shot classification problem, there still remains an important challenge: how to generalize to unseen domains while meta-learning on multiple seen domains? In this paper, we propose an optimization-based meta-learning method, called Combining Domain-Specific Meta-Learners (CosML), that addresses the cross-domain few-shot classification problem. CosML first trains a set of meta-learn…
We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather than fixing the class prototypes to be the Euclidean average of sample embeddings, we allow them to live in a higher-dimensional space (embedded class models) and learn the prototypes along with the model parameters. The class representation function is defined implicitly, which allows us to deal with a variable number of shots per each class with a simple constant-size architecture. The class embedding encompasses metric learning, that …
Few-Shot Learning is the challenge of training a model with only a small amount of data. Many solutions to this problem use meta-learning algorithms, i.e. algorithms that learn to learn. By sampling few-shot tasks from a larger dataset, we can teach these algorithms to solve new, unseen tasks. This document reports my work on meta-learning algorithms for Few-Shot Computer Vision. This work was done during my internship at Sicara, a French company building image recognition solutions for businesses. It contains: 1. an extensive review of the state-of-the-art in few-shot computer vision; 2. a be…
We consider the task of few shot link prediction on graphs. The goal is to learn from a distribution over graphs so that a model is able to quickly infer missing edges in a new graph after a small amount of training. We show that current link prediction methods are generally ill-equipped to handle this task. They cannot effectively transfer learned knowledge from one graph to another and are unable to effectively learn from sparse samples of edges. To address this challenge, we introduce a new gradient-based meta learning framework, Meta-Graph. Our framework leverages higher-order gradients al…
