English
Related papers

Related papers: Structural Disentanglement in Bilinear MLPs via Ar…

200 papers

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

We investigate deep morphological neural networks (DMNNs). We demonstrate that despite their inherent non-linearity, "linear" activations are essential for DMNNs. To preserve their inherent sparsity, we propose architectures that constraint…

Machine Learning · Computer Science 2025-12-24 Konstantinos Fotopoulos , Petros Maragos

In machine learning and neuroscience, certain computational structures and algorithms are known to yield disentangled representations without us understanding why, the most striking examples being perhaps convolutional neural networks and…

Machine Learning · Computer Science 2017-03-21 Gary Bécigneul

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Estimating causal treatment effects in observational settings is frequently compromised by selection bias arising from unobserved confounders. While traditional econometric methods struggle when these confounders are orthogonal to…

Artificial Intelligence · Computer Science 2026-01-06 Ahmed Dawoud , Osama El-Shamy

While neural networks have achieved vastly enhanced performance over traditional iterative methods in many cases, they are generally empirically designed and the underlying structures are difficult to interpret. The algorithm unrolling…

Computer Vision and Pattern Recognition · Computer Science 2019-02-18 Yuelong Li , Mohammad Tofighi , Vishal Monga , Yonina C. Eldar

The ability to selectively remove knowledge from LLMs is highly desirable. However, existing methods often struggle with balancing unlearning efficacy and retain model utility, and lack controllability at inference time to emulate base…

Machine Learning · Computer Science 2025-10-09 William F. Shen , Xinchi Qiu , Meghdad Kurmanji , Alex Iacob , Lorenzo Sani , Yihong Chen , Nicola Cancedda , Nicholas D. Lane

Hypercomplex algebras have recently been gaining prominence in the field of deep learning owing to the advantages of their division algebras over real vector spaces and their superior results when dealing with multidimensional signals in…

Machine Learning · Computer Science 2024-05-14 Danilo Comminiello , Eleonora Grassucci , Danilo P. Mandic , Aurelio Uncini

Efforts to interpret reinforcement learning (RL) models often rely on high-level techniques such as attribution or probing, which provide only correlational insights and coarse causal control. This work proposes replacing nonlinearities in…

Machine Learning · Computer Science 2024-12-03 Narmeen Oozeer , Sinem Erisken , Alice Rigg

Simulation and modeling are essential in product development, integrated into the design and manufacturing process to enhance efficiency and quality. They are typically represented as complex nonlinear differential algebraic equations. The…

Machine Learning · Computer Science 2026-03-25 Wenqiang Yang , Wenyuan Wu , Yong Feng , Changbo Chen

In this paper, we focus on learning structure-aware document representations from data without recourse to a discourse parser or additional annotations. Drawing inspiration from recent efforts to empower neural networks with a structural…

Computation and Language · Computer Science 2018-02-06 Yang Liu , Mirella Lapata

This paper presents an unsupervised multi-modal learning system that learns associative representation from two input modalities, or channels, such that input on one channel will correctly generate the associated response at the other and…

Neural and Evolutionary Computing · Computer Science 2014-01-14 Ti Wang , Daniel L. Silver

Deep neural network architectures have recently produced excellent results in a variety of areas in artificial intelligence and visual recognition, well surpassing traditional shallow architectures trained using hand-designed features. The…

Computer Vision and Pattern Recognition · Computer Science 2016-04-15 Catalin Ionescu , Orestis Vantzos , Cristian Sminchisescu

One of the biggest challenges for deep learning algorithms in medical image analysis is the indiscriminate mixing of image properties, e.g. artifacts and anatomy. These entangled image properties lead to a semantically redundant feature…

Machine Learning · Computer Science 2019-08-22 Qingjie Meng , Nick Pawlowski , Daniel Rueckert , Bernhard Kainz

We describe a basic correspondence between linear algebraic structures within vector embeddings in artificial neural networks and conditional independence constraints on the probability distributions modeled by these networks. Our framework…

Machine Learning · Computer Science 2024-07-15 Matthew Trager , Alessandro Achille , Pramuditha Perera , Luca Zancato , Stefano Soatto

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Computation and Language · Computer Science 2022-10-28 Jiahao Zhao , Wenji Mao

We introduce a principled approach for unsupervised structure learning of deep neural networks. We propose a new interpretation for depth and inter-layer connectivity where conditional independencies in the input distribution are encoded…

Machine Learning · Statistics 2018-10-18 Raanan Y. Rohekar , Shami Nisimov , Yaniv Gurwicz , Guy Koren , Gal Novik

Mechanistic Interpretability aims to reverse engineer the algorithms implemented by neural networks by studying their weights and activations. An obstacle to reverse engineering neural networks is that many of the parameters inside a…

Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…

Disentanglement is a difficult property to enforce in neural representations. This might be due, in part, to a formalization of the disentanglement problem that focuses too heavily on separating relevant factors of variation of the data in…

Machine Learning · Computer Science 2022-05-23 Andrea Valenti , Davide Bacciu