Few-shot classification is a challenging task which aims to formulate the ability of humans to learn concepts from limited prior data and has drawn considerable attention in machine learning. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained to learn the ability of handling classification tasks on extremely large or infinite episodes representing different classification task, each with a small labeled support set and its corresponding query set. In this work, we advance this few-shot classification paradigm by formulating it as a supervised classification learning problem. We further propose multi-episode and cross-way training techniques, which respectively correspond to the minibatch and pretraining in classification problems. Experimental results on a state-of-the-art few-shot classification method (prototypical networks) demonstrate that both the proposed training strategies can highly accelerate the training process without accuracy loss for varying few-shot classification problems on Omniglot and miniImageNet.
Siemens AI Lab（西门子人工智能实验室）；Siemens Technology（西门子科技）；Siemens Digital Industries（西门子数字工业）；Ludwig Maximilian University of Munich（慕尼黑大学）
Although few-shot learning and one-class classification (OCC), i.e., learning a binary classifier with data from only one class, have been separately well studied, their intersection remains rather unexplored. Our work addresses the few-shot OCC problem and presents a method to modify the episodic data sampling strategy of the model-agnostic meta-learning (MAML) algorithm to learn a model initialization particularly suited for learning few-shot OCC tasks. This is done by explicitly optimizing for an initialization which only requires few gradient steps with one-class minibatches to yield a per…
Few-shot knowledge graph (KG) completion task aims to perform inductive reasoning over the KG: given only a few support triplets of a new relation $\bowtie$ (e.g., (chop,$\bowtie$,kitchen), (read,$\bowtie$,library), the goal is to predict the query triplets of the same unseen relation $\bowtie$, e.g., (sleep,$\bowtie$,?). Current approaches cast the problem in a meta-learning framework, where the model needs to be first jointly trained over many training few-shot tasks, each being defined by its own relation, so that learning/prediction on the target few-shot task can be effective. However, in…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Few-shot learning is challenging due to its very limited data and labels. Recent studies in big transfer (BiT) show that few-shot learning can greatly benefit from pretraining on large scale labeled dataset in a different domain. This paper asks a more challenging question: "can we use as few as possible labels for few-shot learning in both pretraining (with no labels) and fine-tuning (with fewer labels)?". Our key insight is that the clustering of target samples in the feature space is all we need for few-shot finetuning. It explains why the vanilla unsupervised pretraining (poor clustering) …
Learning a new task from a handful of examples remains an open challenge in machine learning. Despite the recent progress in few-shot learning, most methods rely on supervised pretraining or meta-learning on labeled meta-training data and cannot be applied to the case where the pretraining data is unlabeled. In this study, we present an unsupervised few-shot learning method via deep Laplacian eigenmaps. Our method learns representation from unlabeled data by grouping similar samples together and can be intuitively interpreted by random walks on augmented training data. We analytically show how…
Deep neural language models have set new breakthroughs in many tasks of Natural Language Processing (NLP). Recent work has shown that deep transformer language models (pretrained on large amounts of texts) can achieve high levels of task-specific few-shot performance comparable to state-of-the-art models. However, the ability of these large language models in few-shot transfer learning has not yet been explored in the biomedical domain. We investigated the performance of two powerful transformer language models, i.e. GPT-3 and BioBERT, in few-shot settings on various biomedical NLP tasks. The …
New York University（纽约大学）；IBM Research AI（IBM研究院人工智能部门）
Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available. To address this, we use supervised pretraining on source-domain data to reduce sample complexity on domain-specific downstream tasks. We evaluate zero-shot performance on domain-specific reading comprehension tasks by combining task transfer with domain adaptation to fine-tune a pretrained model with no labelled data from the target task. Our approach outper…
McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究院）
This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically, we train a linear model over the representations to match different augmented views of the same image together, each view presented sequentially. The linear model is then evaluated on both its ability to classify images it just saw, and also on images from previous iterations. This gives rise to representations that favor quick knowledge retention with minima…
Few-shot NLP research is highly active, yet conducted in disjoint research threads with evaluation suites that lack challenging-yet-realistic testing setups and fail to employ careful experimental design. Consequently, the community does not know which techniques perform best or even if they outperform simple baselines. In response, we formulate the FLEX Principles, a set of requirements and best practices for unified, rigorous, valid, and cost-sensitive few-shot NLP evaluation. These principles include Sample Size Design, a novel approach to benchmark design that optimizes statistical accurac…
MIT EECS（麻省理工学院电气工程与计算机科学系）；MIT Lincoln Lab（麻省理工学院林肯实验室）；MIT CSAIL & BCS（麻省理工学院计算机科学与人工智能实验室及脑与认知科学系）；MIT Physics（麻省理工学院物理系）
Recent advances in deep learning, in particular enabled by hardware advances and big data, have provided impressive results across a wide range of computational problems such as computer vision, natural language, or reinforcement learning. Many of these improvements are however constrained to problems with large-scale curated data-sets which require a lot of human labor to gather. Additionally, these models tend to generalize poorly under both slight distributional shifts and low-data regimes. In recent years, emerging fields such as meta-learning or self-supervised learning have been closing …
We evaluate a simple approach to improving zero-shot multilingual transfer of mBERT on social media corpus by adding a pretraining task called translation pair prediction (TPP), which predicts whether a pair of cross-lingual texts are a valid translation. Our approach assumes access to translations (exact or approximate) between source-target language pairs, where we fine-tune a model on source language task data and evaluate the model in the target language. In particular, we focus on language pairs where transfer learning is difficult for mBERT: those where source and target languages are di…
PatchFormer: A Patch-Based Time Series Foundation Model with Hierarchical Masked Reconstruction and Cross-Domain Transfer Learning for Zero-Shot Multi-Horizon Forecasting
Department of Applied Mathematics and Computer Science (DTU Compute), Technical University of Denmark（应用数学与计算机科学系（DTU Compute），丹麦技术大学）；Department of Engineering, Eskisehir Technical University（工程系，埃斯基谢普大学）；Department of Computer Engineering, Afyon Kocatepe University（计算机工程系，阿菲昂卡奥卡佩大学）
German Research Center for AI（德国人工智能研究中心）；Copenhagen University（哥本哈根大学）
For natural language processing `text-to-text' tasks, the prevailing approaches heavily rely on pretraining large self-supervised models on increasingly larger `task-external' data. Transfer learning from high-resource pretraining works well, but research has focused on settings with very large data and compute requirements, while the potential of efficient low-resource learning, without large `task-external' pretraining, remains under-explored. In this work, we evaluate against three core challenges for resource efficient learning. Namely, we analyze: (1) pretraining data ($X$) efficiency; (2…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Microsoft Research（微软研究院）；Microsoft Cloud + AI（微软云与人工智能）；UCLA（加州大学洛杉矶分校）
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize image regions for object detection leads to poor performance due to a domain shift: CLIP was trained to match an image as a whole to a text description, without capturing the fine-grained alignment between image regions and text spans. To mitigate this issue, we propose a new method called RegionCLIP that significantly extends CLIP to learn region-level visu…
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related languages which is not utilized by these methods. This paper extends previous work on zero-shot cross-lingual transfer learning by fine-tuning a multilingually pretrained wav2vec 2.0 model to transcribe unseen languages. This is done by mapping phonemes of the training languages to the target language using articulatory features. Experiments show that this simple me…
Image geolocalization is the challenging task of predicting the geographic coordinates of origin for a given photo. It is an unsolved problem relying on the ability to combine visual clues with general knowledge about the world to make accurate predictions across geographies. We present $\href{https://huggingface.co/geolocal/StreetCLIP}{\text{StreetCLIP}}$, a robust, publicly available foundation model not only achieving state-of-the-art performance on multiple open-domain image geolocalization benchmarks but also doing so in a zero-shot setting, outperforming supervised models trained on more…
Hugging Face；Google（谷歌）；LightOn；Allen Institute for AI（艾伦人工智能研究所）；LPENS, École Normale Supérieure（巴黎高等师范学院物理实验室）
Large pretrained Transformer language models have been shown to exhibit zero-shot generalization, i.e. they can perform a wide variety of tasks that they were not explicitly trained on. However, the architectures and pretraining objectives used across state-of-the-art models differ significantly, and there has been limited systematic comparison of these factors. In this work, we present a large-scale evaluation of modeling choices and their impact on zero-shot generalization. In particular, we focus on text-to-text models and experiment with three model architectures (causal/non-causal decoder…
University of California, Irvine（加州大学欧文分校）；Microsoft Semantic Machines（微软语义机器公司）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Pretrained Language Models (LMs) have demonstrated ability to perform numerical reasoning by extrapolating from a few examples in few-shot settings. However, the extent to which this extrapolation relies on robust reasoning is unclear. In this paper, we investigate how well these models reason with terms that are less frequent in the pretraining data. In particular, we examine the correlations between the model performance on test instances and the frequency of terms from those instances in the pretraining data. We measure the strength of this correlation for a number of GPT-based language mod…
We propose a multitask pretraining approach ZeroPrompt for zero-shot generalization, focusing on task scaling and zero-shot prompting. While previous models are trained on only a few dozen tasks, we scale to 1,000 tasks for the first time using real-world data. This leads to a crucial discovery that task scaling can be an efficient alternative to model scaling; i.e., the model size has little impact on performance with an extremely large number of tasks. Our results show that task scaling can substantially improve training efficiency by 30 times in FLOPs. Moreover, we present a prompting metho…
University of California, Berkeley（加州大学伯克利分校）；Intel AI Labs（英特尔人工智能实验室）
Being able to predict the performance of circuits without running expensive simulations is a desired capability that can catalyze automated design. In this paper, we present a supervised pretraining approach to learn circuit representations that can be adapted to new circuit topologies or unseen prediction tasks. We hypothesize that if we train a neural network (NN) that can predict the output DC voltages of a wide range of circuit instances it will be forced to learn generalizable knowledge about the role of each circuit element and how they interact with each other. The dataset for this supe…
University of Edinburgh（爱丁堡大学）；WS AI Labs（WS人工智能实验室）；New York University（纽约大学）
Advances in neural modeling have achieved state-of-the-art (SOTA) results on public natural language processing (NLP) benchmarks, at times surpassing human performance. However, there is a gap between public benchmarks and real-world applications where noise, such as typographical or grammatical mistakes, is abundant and can result in degraded performance. Unfortunately, works which evaluate the robustness of neural models on noisy data and propose improvements, are limited to the English language. Upon analyzing noise in different languages, we observe that noise types vary greatly across lan…
Zero-Shot Learning with Subsequence Reordering Pretraining for Compound-Protein Interaction
School of Computer Science, Wuhan University（武汉大学计算机学院）；Engineering Research Center for Big Data Application in Private Health Medicine of Fujian Universities, Putian University（福建省私人健康医学大数据应用工程研究中心，莆田大学）；Macquarie University（麦考瑞大学）；Wuhan University Shenzhen Research Institute（武汉大学深圳研究院）
New York University（纽约大学）；Google（谷歌）；Stanford University（斯坦福大学）；NVIDIA（英伟达）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Baylor College of Medicine（贝勒医学院）；Rice University（莱斯大学）；Columbia University（哥伦比亚大学）；Canadian Institute for Advanced Research（加拿大高等研究院）
Despite impressive progress in deep learning, generalizing far beyond the training distribution is an important open challenge. In this work, we consider few-shot classification, and aim to shed light on what makes some novel classes easier to learn than others, and what types of learned representations generalize better. To this end, we define a new paradigm in terms of attributes -- simple building blocks of which concepts are formed -- as a means of quantifying the degree of relatedness of different concepts. Our empirical analysis reveals that supervised learning generalizes poorly to new …
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization (muP), many optimal HPs remain stable even as model size changes. This leads to a new HP tuning paradigm we call muTransfer: parametrize the target model in muP, tune the HP indirectly on a smaller model, and zero-shot transfer them to the full-sized model, i.e., without directly tuning the latter at all. We verify muTransfer on Transformer and ResNet. For example, 1) by transferring …
BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting
Brown University（布朗大学）；EleutherAI；Yale University（耶鲁大学）；Hugging Face；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；University College London（伦敦大学学院）；PSAU（沙特王子萨塔姆·本·阿卜杜勒阿齐兹大学）；Nanyang Technological University（南洋理工大学）；University of Washington（华盛顿大学）；University of Oregon（俄勒冈大学）；The Hong Kong University of Science and Technology（香港科技大学）；Booz Allen Hamilton（博思艾伦咨询公司）；NAVER LABS Europe（NAVER欧洲实验室）
Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretraining
Department of Computer Science, The University of Hong Kong（香港大学计算机科学系）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；Department of Information Systems and Management Engineering, Southern University of Science and Technology（南方科技大学信息 systems 和管理工程系）
HeterCSI: Channel-Adaptive Heterogeneous CSI Pretraining Framework for Generalized Wireless Foundation Models
National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications（中国移动网络技术国家工程研究中心，北京邮电大学）；Department of Broadband Communication, Pengcheng Laboratory（宽带通信系，鹏城实验室）；Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China（民族语言智能分析与安全治理重点实验室，中央民族大学）；China Telecom Corporation Limited Gansu Branch（中国电信集团甘肃分公司）
