English
Related papers

Related papers: Approximating Human-Like Few-shot Learning with GP…

200 papers

We challenge the prevailing assumption that LLMs must rely fully on sub-word tokens for high-quality text generation. To this end, we propose the "Generative Pretrained Thoughtformer" (GPTHF), a hierarchical transformer language model…

Computation and Language · Computer Science 2025-03-17 David Gu , Peter Belcak , Roger Wattenhofer

The meta learning few-shot classification is an emerging problem in machine learning that received enormous attention recently, where the goal is to learn a model that can quickly adapt to a new task with only a few labeled data. We…

Machine Learning · Computer Science 2021-12-14 Minyoung Kim , Timothy Hospedales

Learning transferable representation of knowledge graphs (KGs) is challenging due to the heterogeneous, multi-relational nature of graph structures. Inspired by Transformer-based pretrained language models' success on learning transferable…

Computation and Language · Computer Science 2023-03-29 Sanxing Chen , Hao Cheng , Xiaodong Liu , Jian Jiao , Yangfeng Ji , Jianfeng Gao

Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…

Machine Learning · Computer Science 2023-07-11 Zihao Jiang , Yunkai Dang , Dong Pang , Huishuai Zhang , Weiran Huang

Standard lossy image compression algorithms aim to preserve an image's appearance, while minimizing the number of bits needed to transmit it. However, the amount of information actually needed by a user for downstream tasks -- e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-10 Siddharth Reddy , Anca D. Dragan , Sergey Levine

Although data-free incremental learning methods are memory-friendly, accurately estimating and counteracting representation shifts is challenging in the absence of historical data. This paper addresses this thorny problem by proposing a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Zhiheng Ma , Xiaopeng Hong , Beinan Liu , Yabin Wang , Pinyue Guo , Huiyun Li

We introduce an RG-inspired coarse-graining for extracting the collective features of data. The key to successful coarse-graining lies in finding appropriate pairs of data sets. We coarse-grain the two closest data in a regular real-space…

Data Analysis, Statistics and Probability · Physics 2023-07-19 Jonathan Landy , Tsvi Tlusty , YeongKyu Lee , YongSeok Jho

We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first…

Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images.…

Robotics · Computer Science 2024-01-22 Koki Yamane , Sho Sakaino , Toshiaki Tsuji

State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks. However, they still fail to provide satisfactory results in scarce data regimes. To a certain extent this lack of data can be compensated…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Frederik Pahde , Oleksiy Ostapenko , Patrick Jähnichen , Tassilo Klein , Moin Nabi

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs…

Computation and Language · Computer Science 2023-12-07 Huiqiang Jiang , Qianhui Wu , Chin-Yew Lin , Yuqing Yang , Lili Qiu

Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant…

Computation and Language · Computer Science 2023-01-10 Aleksandra Edwards , Asahi Ushio , Jose Camacho-Collados , Hélène de Ribaupierre , Alun Preece

Cold-start problem is a fundamental challenge for recommendation tasks. The recent self-supervised learning (SSL) on Graph Neural Networks (GNNs) model, PT-GNN, pre-trains the GNN model to reconstruct the cold-start embeddings and has shown…

Information Retrieval · Computer Science 2022-05-24 Bowen Hao , Hongzhi Yin , Jing Zhang , Cuiping Li , Hong Chen

Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…

Computation and Language · Computer Science 2021-07-23 Junghoon Lee , Jounghee Kim , Pilsung Kang

Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the…

Machine Learning · Computer Science 2021-03-23 Kaidi Cao , Maria Brbic , Jure Leskovec

The ability to precisely quantify similarity between various entities has been a fundamental complication in various problem spaces specifically in the classification of cellular images. Contemporary similarity measures applied in the…

Computer Vision and Pattern Recognition · Computer Science 2018-12-04 D Yoan L. Mekontchou Yomba

This work proposes the extended functional tensor train (EFTT) format for compressing and working with multivariate functions on tensor product domains. Our compression algorithm combines tensorized Chebyshev interpolation with a low-rank…

Numerical Analysis · Mathematics 2024-05-30 Christoph Strössner , Bonan Sun , Daniel Kressner

Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples. Requiring a large number of data samples, many deep learning solutions suffer from data hunger and extensively high…

Machine Learning · Computer Science 2022-03-10 Archit Parnami , Minwoo Lee

Meta learning approaches to few-shot classification are computationally efficient at test time, requiring just a few optimization steps or single forward pass to learn a new task, but they remain highly memory-intensive to train. This…

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…

Computer Vision and Pattern Recognition · Computer Science 2019-04-10 Qianru Sun , Yaoyao Liu , Tat-Seng Chua , Bernt Schiele