Cooperative artificial intelligence with human or superhuman proficiency in collaborative tasks stands at the frontier of machine learning research. Prior work has tended to evaluate cooperative AI performance under the restrictive paradigms of self-play (teams composed of agents trained together) and cross-play (teams of agents trained independently but using the same algorithm). Recent work has indicated that AI optimized for these narrow settings may make for undesirable collaborators in the real-world. We formalize an alternative criteria for evaluating cooperative AI, referred to as inter-algorithm cross-play, where agents are evaluated on teaming performance with all other agents within an experiment pool with no assumption of algorithmic similarities between agents. We show that existing state-of-the-art cooperative AI algorithms, such as Other-Play and Off-Belief Learning, under-perform in this paradigm. We propose the Any-Play learning augmentation -- a multi-agent extension of diversity-based intrinsic rewards for zero-shot coordination (ZSC) -- for generalizing self-play-based algorithms to the inter-algorithm cross-play setting. We apply the Any-Play learning augmentation to the Simplified Action Decoder (SAD) and demonstrate state-of-the-art performance in the collaborative card game Hanabi.
Automatic Curriculum Design for Zero-Shot Human-AI Coordination
Department of AI Convergence, Gwangju Institute of Science and Technology（人工智能融合系，全州科学技术研究院）；School of Integrated Technology, Gwangju Institute of Science and Technology（整合技术学院，全州科学技术研究院）
Facebook AI Research（脸书人工智能研究院）；University of Oxford（牛津大学）
The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions ("handshakes") and are not compatible with other, independently trained agents or humans. This latter desiderata was recently formalized by Hu et al. 2020 as the zero-shot coordination (ZSC) setting and partially addressed with their Other-Play (OP) algorithm, which showed improved ZSC and human-AI performance in the card game Hanabi. OP assumes access to the symmetries of th…
A New Formalism, Method and Open Issues for Zero-Shot Coordination
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；University of California, Berkeley（加州大学伯克利分校）；Duke University（杜克大学）；Facebook AI Research（脸书人工智能研究院）
We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e.g. humans). Standard Multi-Agent Reinforcement Learning (MARL) methods typically focus on the self-play (SP) setting where agents construct strategies by playing the game with themselves repeatedly. Unfortunately, applying SP naively to the zero-shot coordination problem can produce agents that establish highly specialized conventions that do not carry over to novel partners they have not been trained with. We introduce a novel learning algorithm calle…
Yonsei University（延世大学）；NAVER AI Lab（NAVER人工智能实验室）；Changwon National University（昌原大学）
Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great performance boosts. However, they have not been designed to capture the intricate compositional structure of natural language. As a result, they fail to generate samples with plausible and diverse sentence structures. Motivated by this, we present the data Augmentation using Lexicalized Probabilistic context-free grammars (ALP) that generates augmented samples with diverse syntactic structures with plausible grammar. …
Recent advances in large pre-trained language models (PLMs) lead to impressive gains in natural language understanding (NLU) tasks with task-specific fine-tuning. However, directly fine-tuning PLMs heavily relies on sufficient labeled training instances, which are usually hard to obtain. Prompt-based tuning on PLMs has shown to be powerful for various downstream few-shot tasks. Existing works studying prompt-based tuning for few-shot NLU tasks mainly focus on deriving proper label words with a verbalizer or generating prompt templates to elicit semantics from PLMs. In addition, conventional da…
PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；King’s College London（伦敦国王学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；The University of Sydney（悉尼大学）；University College London（伦敦大学学院）
We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without relying on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention. Our approach solves perfectly the one-shot image classification Omniglot challenge. Our model exceeds human level accuracy, as well as the previous state of the art, with no data augmentation.
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）
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
Large datasets' availability is catalyzing a rapid expansion of deep learning in general and computer vision in particular. At the same time, in many domains, a sufficient amount of training data is lacking, which may become an obstacle to the practical application of computer vision techniques. This paper challenges small and imbalanced datasets based on the example of a plant phenomics domain. We introduce an image augmentation framework, which enables us to extremely enlarge the number of training samples while providing the data for such tasks as object detection, semantic segmentation, in…
Cross-Modal Augmentation for Few-Shot Multimodal Fake News Detection
College of Information Science and Technology, Qingdao University of Science and Technology（青岛科技大学信息科学与技术学院）；College of Data Science, Qingdao University of Science and Technology（青岛科技大学数据科学学院）；University of Sheffield（谢菲尔德大学）
Enhance Then Search: An Augmentation-Search Strategy with Foundation Models for Cross-Domain Few-Shot Object Detection
Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）；Wuhan University（武汉大学）；University of Science and Technology of China（中国科学技术大学）
Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Indiana University（印第安纳大学）；University of Maryland（马里兰大学）；Google Research（谷歌研究院）；Amazon Lab126（亚马逊Lab126）；Reykjavik University（雷克雅未克大学）
Beijing Institute of Technology（北京理工大学）；Capital Medical University（首都医科大学）；Beijing Tiantan Hospital（北京天坛医院）
Deep learning based methods have achieved state-of-the-art performance for automated white matter (WM) tract segmentation. In these methods, the segmentation model needs to be trained with a large number of manually annotated scans, which can be accumulated throughout time. When novel WM tracts, i.e., tracts not included in the existing annotated WM tracts, are to be segmented, additional annotations of these novel WM tracts need to be collected. Since tract annotation is time-consuming and costly, it is desirable to make only a few annotations of novel WM tracts for training the segmentation …
A bottleneck to developing Semantic Parsing (SP) models is the need for a large volume of human-labeled training data. Given the complexity and cost of human annotation for SP, labeled data is often scarce, particularly in multilingual settings. Large Language Models (LLMs) excel at SP given only a few examples, however LLMs are unsuitable for runtime systems which require low latency. In this work, we propose CLASP, a simple method to improve low-resource SP for moderate-sized models: we generate synthetic data from AlexaTM 20B to augment the training set for a model 40x smaller (500M paramet…
Istanbul Technical University（伊斯坦布尔技术大学）；Faculty of Medicine of Sousse（苏塞医学院）；Imperial College London（伦敦帝国学院）
The challenges of collecting medical data on neurological disorder diagnosis problems paved the way for learning methods with scarce number of samples. Due to this reason, one-shot learning still remains one of the most challenging and trending concepts of deep learning as it proposes to simulate the human-like learning approach in classification problems. Previous studies have focused on generating more accurate fingerprints of the population using graph neural networks (GNNs) with connectomic brain graph data. Thereby, generated population fingerprints named connectional brain template (CBTs…
Tencent AI Lab（腾讯人工智能实验室）；Tsinghua University（清华大学）
We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data. Although such agents can be obtained through self-play training, they can suffer significantly from distributional shift when paired with unencountered partners, such as humans. To mitigate this distributional shift, we propose Maximum Entropy Population-based training (MEP). In MEP, agents in the population are trained with our derived Population Entropy bonus to promote both pairwise diversity between agents and individual diversity of agents themselves, and a …
In many applications of machine learning, certain categories of examples may be underrepresented in the training data, causing systems to underperform on such "few-shot" cases at test time. A common remedy is to perform data augmentation, such as by duplicating underrepresented examples, or heuristically synthesizing new examples. But these remedies often fail to cover the full diversity and complexity of real examples. We propose a data augmentation approach that performs neural Example Extrapolation (Ex2). Given a handful of exemplars sampled from some distribution, Ex2 synthesizes new examp…
FSL-Rectifier: Rectify Outliers in Few-Shot Learning via Test-Time Augmentation
National University of Singapore（新加坡国立大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Guangdong Lab of AI and Digital Economy (SZ)（广东人工智能与数字经济实验室（深圳））
This work focuses on in-context data augmentation for intent detection. Having found that augmentation via in-context prompting of large pre-trained language models (PLMs) alone does not improve performance, we introduce a novel approach based on PLMs and pointwise V-information (PVI), a metric that can measure the usefulness of a datapoint for training a model. Our method first fine-tunes a PLM on a small seed of training data and then synthesizes new datapoints - utterances that correspond to given intents. It then employs intent-aware filtering, based on PVI, to remove datapoints that are n…
Columbia University（哥伦比亚大学）；Amazon Alexa AI（亚马逊Alexa人工智能部门）
Dialogue understanding tasks often necessitate abundant annotated data to achieve good performance and that presents challenges in low-resource settings. To alleviate this barrier, we explore few-shot data augmentation for dialogue understanding by prompting large pre-trained language models and present a novel approach that iterates on augmentation quality by applying weakly-supervised filters. We evaluate our methods on the emotion and act classification tasks in DailyDialog and the intent classification task in Facebook Multilingual Task-Oriented Dialogue. Models fine-tuned on our augmented…
Gotta: Generative Few-shot Question Answering by Prompt-based Cloze Data Augmentation
University of California, Los Angeles（加州大学洛杉矶分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Univ of Technology Sydney（悉尼科技大学）；Amazon Search（亚马逊搜索）
Stanford University（斯坦福大学）；NVIDIA（英伟达）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；California Institute of Technology（加州理工学院）
Generalization has been a long-standing challenge for reinforcement learning (RL). Visual RL, in particular, can be easily distracted by irrelevant factors in high-dimensional observation space. In this work, we consider robust policy learning which targets zero-shot generalization to unseen visual environments with large distributional shift. We propose SECANT, a novel self-expert cloning technique that leverages image augmentation in two stages to decouple robust representation learning from policy optimization. Specifically, an expert policy is first trained by RL from scratch with weak aug…
University of Washington（华盛顿大学）；Facebook AI Research（脸书人工智能研究院）
We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified. On the Spider, Sparc, an…
Chongqing University（重庆大学）；University of Delaware（特拉华大学）
Data augmentation is a powerful technique for improving the performance of the few-shot classification task. It generates more samples as supplements, and then this task can be transformed into a common supervised learning issue for solution. However, most mainstream data augmentation based approaches only consider the single modality information, which leads to the low diversity and quality of generated features. In this paper, we present a novel multi-modal data augmentation approach named Dizygotic Conditional Variational AutoEncoder (DCVAE) for addressing the aforementioned issue. DCVAE co…
