English
Related papers

Related papers: Layerwise Dynamics for In-Context Classification i…

200 papers

Multi-label classification has broad applications and depends on powerful representations capable of capturing multi-label interactions. We introduce \textit{Diff-Feat}, a simple but powerful framework that extracts intermediate features…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Tian Lan , Yiming Zheng , Jianxin Yin

Large autoregressive models like Transformers can solve tasks through in-context learning (ICL) without learning new weights, suggesting avenues for efficiently solving new tasks. For many tasks, e.g., linear regression, the data…

Machine Learning · Computer Science 2025-06-17 Sarthak Mittal , Eric Elmoznino , Leo Gagnon , Sangnie Bhardwaj , Tom Marty , Dhanya Sridhar , Guillaume Lajoie

The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient…

Computation and Language · Computer Science 2024-03-12 Hui Ye , Rajshekhar Sunderraman , Shihao Ji

Understanding the intricate non-convex training dynamics of softmax-based models is crucial for explaining the empirical success of transformers. In this article, we analyze the gradient flow dynamics of the value-softmax model, defined as…

Machine Learning · Computer Science 2026-03-09 Aditya Varre , Mark Rofin , Nicolas Flammarion

Recently introduced by some of the authors, the in-context identification paradigm aims at estimating, offline and based on synthetic data, a meta-model that describes the behavior of a whole class of systems. Once trained, this meta-model…

Machine Learning · Computer Science 2024-10-07 Matteo Rufolo , Dario Piga , Gabriele Maroni , Marco Forgione

We present a novel framework to exploit privileged information for recognition which is provided only during the training phase. Here, we focus on recognition task where images are provided as the main view and soft biometric traits…

Computer Vision and Pattern Recognition · Computer Science 2020-09-07 Seyed Mehdi Iranmanesh , Ali Dabouei , Nasser M. Nasrabadi

Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often obtained as the sum of two contributions: a residual path that copies the input and the…

Multi-label classification problems with thousands of classes are hard to solve with in-context learning alone, as language models (LMs) might lack prior knowledge about the precise classes or how to assign them, and it is generally…

Computation and Language · Computer Science 2024-01-23 Karel D'Oosterlinck , Omar Khattab , François Remy , Thomas Demeester , Chris Develder , Christopher Potts

This paper introduces an algorithm to select demonstration examples for in-context learning of a query set. Given a set of $n$ examples, how can we quickly select $k$ out of $n$ to best serve as the conditioning for downstream inference?…

Machine Learning · Computer Science 2025-11-05 Ziniu Zhang , Zhenshuo Zhang , Dongyue Li , Lu Wang , Jennifer Dy , Hongyang R. Zhang

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Martina G. Vilas , Timothy Schaumlöffel , Gemma Roig

Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels. Hence, scalability of the classifier with increasing label dimension is an important consideration. In…

Machine Learning · Computer Science 2023-04-24 Istasis Mishra , Arpan Dasgupta , Pratik Jawanpuria , Bamdev Mishra , Pawan Kumar

This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding. Current solutions for this task usually rely on an extra step of extracting…

Computer Vision and Pattern Recognition · Computer Science 2017-11-09 Zhouxia Wang , Tianshui Chen , Guanbin Li , Ruijia Xu , Liang Lin

Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks.…

Machine Learning · Statistics 2011-10-27 Jasper Snoek , Ryan Prescott Adams , Hugo Larochelle

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…

Machine Learning · Computer Science 2024-11-21 Xuechen Zhang , Xiangyu Chang , Mingchen Li , Amit Roy-Chowdhury , Jiasi Chen , Samet Oymak

We propose TabTransformer, a novel deep tabular data modeling architecture for supervised and semi-supervised learning. The TabTransformer is built upon self-attention based Transformers. The Transformer layers transform the embeddings of…

Machine Learning · Computer Science 2020-12-15 Xin Huang , Ashish Khetan , Milan Cvitkovic , Zohar Karnin

Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning…

Machine Learning · Computer Science 2025-07-31 Lorenzo Volpi , Alejandro Moreo , Fabrizio Sebastiani

This paper studies a text classification algorithm based on an improved Transformer to improve the performance and efficiency of the model in text classification tasks. Aiming at the shortcomings of the traditional Transformer model in…

Computation and Language · Computer Science 2025-01-24 Jia Gao , Guiran Liu , Binrong Zhu , Shicheng Zhou , Hongye Zheng , Xiaoxuan Liao

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this paper, we analyze Transformers through the lens of rank…

In multi-label classification, where a single example may be associated with several class labels at the same time, the ability to model dependencies between labels is considered crucial to effectively optimize non-decomposable evaluation…

Machine Learning · Computer Science 2021-06-23 Michael Rapp , Eneldo Loza Mencía , Johannes Fürnkranz , Eyke Hüllermeier

While random demonstration labels barely hurt in-context learning (Min et al., 2022), we show that homogeneous labels--even semantically valid ones--collapse accuracy to <=12% across six models (Pythia, Llama, Qwen; 0.8B--8B) and four…

Machine Learning · Computer Science 2026-05-12 Ming Liu
‹ Prev 1 4 5 6 7 8 10 Next ›