English
Related papers

Related papers: Linear Representation Transferability Hypothesis: …

200 papers

Large Language Models (LLMs) have the capacity to store and recall facts. Through experimentation with open-source models, we observe that this ability to retrieve facts can be easily manipulated by changing contexts, even without altering…

Computation and Language · Computer Science 2024-12-02 Yibo Jiang , Goutham Rajendran , Pradeep Ravikumar , Bryon Aragam

Scattering networks are a class of designed Convolutional Neural Networks (CNNs) with fixed weights. We argue they can serve as generic representations for modelling images. In particular, by working in scattering space, we achieve…

Interpretability and explainability of AI are becoming increasingly important in light of the rapid development of large language models (LLMs). This paper investigates the interpretation of LLMs in the context of the knowledge-based…

Computation and Language · Computer Science 2024-06-05 Valeriya Goloviznina , Evgeny Kotelnikov

Financial transactions constitute connections between entities and through these connections a large scale heterogeneous weighted graph is formulated. In this labyrinth of interactions that are continuously updated, there exists a variety…

Machine Learning · Computer Science 2020-07-02 Antonia Gogoglou , Brian Nguyen , Alan Salimov , Jonathan Rider , C. Bayan Bruss

Transfer learning, also referred as knowledge transfer, aims at reusing knowledge from a source dataset to a similar target one. While many empirical studies illustrate the benefits of transfer learning, few theoretical results are…

Statistics Theory · Mathematics 2021-02-19 David Obst , Badih Ghattas , Jairo Cugliari , Georges Oppenheim , Sandra Claudel , Yannig Goude

Model stitching (Lenc & Vedaldi 2015) is a compelling methodology to compare different neural network representations, because it allows us to measure to what degree they may be interchanged. We expand on a previous work from Bansal,…

Machine Learning · Computer Science 2023-09-04 Adriano Hernandez , Rumen Dangovski , Peter Y. Lu , Marin Soljacic

Deep neural networks such as BERT have made great progress in relation classification. Although they can achieve good performance, it is still a question of concern whether these models recognize the directionality of relations, especially…

Computation and Language · Computer Science 2021-12-02 Shengfei Lyu , Xingyu Wu , Jinlong Li , Qiuju Chen , Huanhuan Chen

Learning from interpretation transition (LFIT) is a framework for learning rules from observed state transitions. LFIT has been implemented in purely symbolic algorithms, but they are unable to deal with noise or generalize to unobserved…

Machine Learning · Computer Science 2024-08-21 Yin Jun Phua , Katsumi Inoue

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

Computation and Language · Computer Science 2024-10-29 Zheng Zhao , Yftah Ziser , Shay B. Cohen

Deep Neural Networks (DNNs) demonstrate remarkable capabilities in learning complex hierarchical data representations, but the nature of these representations remains largely unknown. Existing global explainability methods, such as Network…

Machine Learning · Computer Science 2024-01-19 Kirill Bykov , Laura Kopf , Shinichi Nakajima , Marius Kloft , Marina M. -C. Höhne

We propose a method combining relational-logic representations with neural network learning. A general lifted architecture, possibly reflecting some background domain knowledge, is described through relational rules which may be handcrafted…

Artificial Intelligence · Computer Science 2015-10-14 Gustav Sourek , Vojtech Aschenbrenner , Filip Zelezny , Ondrej Kuzelka

When and why representations learned by different deep neural networks are similar is an active research topic. We choose to address these questions from the perspective of identifiability theory, which suggests that a measure of…

Machine Learning · Computer Science 2025-10-20 Beatrix M. G. Nielsen , Emanuele Marconato , Andrea Dittadi , Luigi Gresele

Contrastive learning has shown to learn better quality representations than models trained using cross-entropy loss. They also transfer better to downstream datasets from different domains. However, little work has been done to explore the…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Alvin De Jun Tan , Clement Tan , Chai Kiat Yeo

Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may…

Machine Learning · Computer Science 2018-08-21 Pan Xiao , Bo Du , Jia Wu , Lefei Zhang , Ruimin Hu , Xuelong Li

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Machine Learning · Computer Science 2026-02-10 Zahra Rahimi Afzal , Tara Esmaeilbeig , Mojtaba Soltanalian , Mesrob I. Ohannessian

Recent literature suggests that the bigger the model, the more likely it is to converge to similar, ``universal'' representations, despite different training objectives, datasets, or modalities. While this literature shows that there is an…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Matéo Mahaut , Marco Baroni

This work proposes an algorithm for explicitly constructing a pair of neural networks that linearize and reconstruct an embedded submanifold, from finite samples of this manifold. Our such-generated neural networks, called Flattening…

Machine Learning · Computer Science 2023-09-11 Michael Psenka , Druv Pai , Vishal Raman , Shankar Sastry , Yi Ma

Humans can flexibly generalize knowledge across domains by leveraging structured relational representations. While prior research has shown how such representations support analogical reasoning, less is known about how they are recruited to…

Artificial Intelligence · Computer Science 2025-12-01 Guillermo Puebla , Leonidas A. A. Doumas

Planning is a crucial element of both human intelligence and contemporary large language models (LLMs). In this paper, we initiate a theoretical investigation into the emergence of planning capabilities in Transformer-based LLMs via their…

Machine Learning · Computer Science 2024-11-12 Siwei Wang , Yifei Shen , Shi Feng , Haoran Sun , Shang-Hua Teng , Wei Chen

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

Machine Learning · Computer Science 2021-05-06 Kurtland Chua , Qi Lei , Jason D. Lee