English
Related papers

Related papers: Tracing Representation Progression: Analyzing and …

200 papers

This paper reveals a novel linear characteristic exclusive to transformer decoders, including models such as GPT, LLaMA, OPT, BLOOM and others. We analyze embedding transformations between sequential layers, uncovering a near-perfect linear…

Deep networks learn internal representations whose geometry--how features bend, rotate, and evolve--affects both generalization and robustness. Existing similarity measures such as CKA or SVCCA capture pointwise overlap between activation…

Machine Learning · Computer Science 2026-01-30 Vasileios Sevetlidis , George Pavlidis

Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks, often performing well on specific task by leveraging input-output examples. Despite their empirical success, a comprehensive…

Machine Learning · Computer Science 2025-06-03 Yifan Hao , Chenlu Ye , Chi Han , Tong Zhang

We explore and expand the $\textit{Soft Nearest Neighbor Loss}$ to measure the $\textit{entanglement}$ of class manifolds in representation space: i.e., how close pairs of points from the same class are relative to pairs of points from…

Machine Learning · Statistics 2019-02-07 Nicholas Frosst , Nicolas Papernot , Geoffrey Hinton

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

Learning informative representations of data is one of the primary goals of deep learning, but there is still little understanding as to what representations a neural network actually learns. To better understand this, subspace match was…

Machine Learning · Computer Science 2019-01-07 Jeremiah Johnson

Centered kernel alignment (CKA) is a popular metric for comparing representations, determining equivalence of networks, and neuroscience research. However, CKA does not account for the underlying manifold and relies on numerous heuristics…

Machine Learning · Computer Science 2025-10-28 Mohammad Tariqul Islam , Du Liu , Deblina Sarkar

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

We analyze subliminal transfer in Transformer models, where a teacher embeds hidden traits that can be linearly decoded by a student without degrading main-task performance. Prior work often attributes transferability to global…

Signal Processing · Electrical Eng. & Systems 2026-02-17 Ayşe Selin Okatan , Mustafa İlhan Akbaş , Laxima Niure Kandel , Berker Peköz

Neural responses encode information that is useful for a variety of downstream tasks. A common approach to understand these systems is to build regression models or ``decoders'' that reconstruct features of the stimulus from neural…

Machine Learning · Statistics 2024-11-14 Sarah E. Harvey , David Lipshutz , Alex H. Williams

The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…

Computer Vision and Pattern Recognition · Computer Science 2023-10-10 Gengwei Zhang , Liyuan Wang , Guoliang Kang , Ling Chen , Yunchao Wei

It is widely believed that learning good representations is one of the main reasons for the success of deep neural networks. Although highly intuitive, there is a lack of theory and systematic approach quantitatively characterizing what…

Machine Learning · Computer Science 2018-11-30 Liwei Wang , Lunjia Hu , Jiayuan Gu , Yue Wu , Zhiqiang Hu , Kun He , John Hopcroft

We employ a toolset -- dubbed Dr. Frankenstein -- to analyse the similarity of representations in deep neural networks. With this toolset, we aim to match the activations on given layers of two trained neural networks by joining them with a…

Machine Learning · Computer Science 2021-10-28 Adrián Csiszárik , Péter Kőrösi-Szabó , Ákos K. Matszangosz , Gergely Papp , Dániel Varga

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…

Machine Learning · Computer Science 2024-03-19 Yihao Xue , Eric Gan , Jiayi Ni , Siddharth Joshi , Baharan Mirzasoleiman

Intermediate features at different layers of a deep neural network are known to be discriminative for visual patterns of different complexities. However, most existing works ignore such cross-layer heterogeneities when classifying samples…

Computer Vision and Pattern Recognition · Computer Science 2016-07-20 Xiaojie Jin , Yunpeng Chen , Jian Dong , Jiashi Feng , Shuicheng Yan

Deep learning models develop successive representations of their input in sequential layers, the last of which maps the final representation to the output. Here we investigate the informational content of these representations by observing…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Benjamin L. Badger

Representation multi-task learning (MTL) has achieved tremendous success in practice. However, the theoretical understanding of these methods is still lacking. Most existing theoretical works focus on cases where all tasks share the same…

Machine Learning · Statistics 2025-07-08 Ye Tian , Yuqi Gu , Yang Feng

Current research has found that some deep neural networks exhibit strong hierarchical self-similarity in feature representation or parameter distribution. However, aside from preliminary studies on how the power-law distribution of weights…

Machine Learning · Computer Science 2025-07-25 Jingyi Ding , Chengwen Qi , Hongfei Wang , Jianshe Wu , Licheng Jiao , Yuwei Guo , Jian Gao