English
Related papers

Related papers: Why self-attention is Natural for Sequence-to-Sequ…

200 papers

Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings. In this work, we propose a novel self-supervised approach…

Audio and Speech Processing · Electrical Eng. & Systems 2022-01-19 Yifan Sun , Xihong Wu

We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty…

Machine Learning · Computer Science 2024-05-10 Mridul Mahajan , Georgios Tzannetos , Goran Radanovic , Adish Singla

Deep neural networks are composed of layers of parametrised linear operations intertwined with non linear activations. In basic models, such as the multi-layer perceptron, a linear layer operates on a simple input vector embedding of the…

Machine Learning · Computer Science 2020-03-06 Jean-Marc Andreoli

Joint-embedding self-supervised learning (SSL) commonly relies on transformations such as data augmentation and masking to learn visual representations, a task achieved by enforcing invariance or equivariance with respect to these…

Computer Vision and Pattern Recognition · Computer Science 2026-01-12 Hafez Ghaemi , Eilif Muller , Shahab Bakhtiari

Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities. We propose two novel approaches to…

Computation and Language · Computer Science 2017-04-24 Jindřich Libovický , Jindřich Helcl

Syntactic structure of sentences in a document substantially informs about its authorial writing style. Sentence representation learning has been widely explored in recent years and it has been shown that it improves the generalization of…

Computation and Language · Computer Science 2022-02-25 Fereshteh Jafariakinabad , Kien A. Hua

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

We formulate an attention mechanism for continuous and ordered sequences that explicitly functions as an alignment model, which serves as the core of many sequence-to-sequence tasks. Standard scaled dot-product attention relies on…

Machine Learning · Computer Science 2025-09-19 Hyungjoon Soh , Junghyo Jo

We argue that time series analysis is fundamentally different in nature to either vision or natural language processing with respect to the forms of meaningful self-supervised learning tasks that can be defined. Motivated by this insight,…

Machine Learning · Computer Science 2023-12-13 Navid Mohammadi Foumani , Chang Wei Tan , Geoffrey I. Webb , Hamid Rezatofighi , Mahsa Salehi

Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…

Computation and Language · Computer Science 2018-05-24 Jonggu Kim , Doyeon Kong , Jong-Hyeok Lee

Convolutions encode equivariance symmetries into neural networks leading to better generalisation performance. However, symmetries provide fixed hard constraints on the functions a network can represent, need to be specified in advance, and…

Machine Learning · Computer Science 2023-10-11 Tycho F. A. van der Ouderaa , Alexander Immer , Mark van der Wilk

Differentiable physical networks provide a simple setting in which learning can be studied through the interaction between trainable parameters and physical equilibrium constraints. We investigate sequential learning in differentiable…

Machine Learning · Computer Science 2026-05-05 Maniru Ibrahim

We consider the statistical problem of learning common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach…

Machine Learning · Statistics 2016-05-12 Uri Shaham , Roy Lederman

Equivariant networks have been adopted in many 3-D learning areas. Here we identify a fundamental limitation of these networks: their ambiguity to symmetries. Equivariant networks cannot complete symmetry-dependent tasks like segmenting a…

Computer Vision and Pattern Recognition · Computer Science 2022-11-01 Sidhika Balachandar , Adrien Poulenard , Congyue Deng , Leonidas Guibas

Representations learnt through deep neural networks tend to be highly informative, but opaque in terms of what information they learn to encode. We introduce an approach to probabilistic modelling that learns to represent data with two…

Machine Learning · Statistics 2019-05-21 Ilya Feige

The words of a language reflect the structure of the human mind, allowing us to transmit thoughts between individuals. However, language can represent only a subset of our rich and detailed cognitive architecture. Here, we ask what kinds of…

Computation and Language · Computer Science 2018-03-07 Gabriel Grand , Idan Asher Blank , Francisco Pereira , Evelina Fedorenko

Attention mechanism has gained great success in vision recognition. Many works are devoted to improving the effectiveness of attention mechanism, which finely design the structure of the attention operator. These works need lots of…

Computer Vision and Pattern Recognition · Computer Science 2022-09-14 Shanshan Zhong , Wushao Wen , Jinghui Qin

Playlists have become a significant part of our listening experience because of the digital cloud-based services such as Spotify, Pandora, Apple Music. Owing to the meteoric rise in the usage of playlists, recommending playlists is crucial…

Information Retrieval · Computer Science 2020-07-28 Piyush Papreja , Hemanth Venkateswara , Sethuraman Panchanathan

Transformer-based language models are trained on large datasets to predict the next token given an input sequence. Despite this simple training objective, they have led to revolutionary advances in natural language processing. Underlying…

Machine Learning · Computer Science 2024-03-14 Yingcong Li , Yixiao Huang , M. Emrullah Ildiz , Ankit Singh Rawat , Samet Oymak

Modeling the structure of coherent texts is a key NLP problem. The task of coherently organizing a given set of sentences has been commonly used to build and evaluate models that understand such structure. We propose an end-to-end…

Computation and Language · Computer Science 2017-12-25 Lajanugen Logeswaran , Honglak Lee , Dragomir Radev