English
Related papers

Related papers: Structured Multidimensional Representation Learnin…

200 papers

We introduce a new construction of embeddings of arbitrary recursive data structures into high dimensional vectors. These embeddings provide an interpretable model for the latent state vectors of transformers. We demonstrate that these…

Machine Learning · Computer Science 2023-11-22 Joshua Maher

For sequence models with large vocabularies, a majority of network parameters lie in the input and output layers. In this work, we describe a new method, DeFINE, for learning deep token representations efficiently. Our architecture uses a…

Computation and Language · Computer Science 2020-02-07 Sachin Mehta , Rik Koncel-Kedziorski , Mohammad Rastegari , Hannaneh Hajishirzi

In this work we investigate a specific transfer learning approach for deep reinforcement learning in the context where the internal dynamics between two tasks are the same but the visual representations differ. We learn a low-dimensional…

Machine Learning · Computer Science 2021-11-24 Geoffrey van Driessel , Vincent Francois-Lavet

In this era of big data, data analytics and machine learning, it is imperative to find ways to compress large data sets such that intrinsic features necessary for subsequent analysis are not lost. The traditional workhorse for data…

Numerical Analysis · Mathematics 2020-01-03 Misha Kilmer , Lior Horesh , Haim Avron , Elizabeth Newman

Tensor Ring (TR) decomposition is a powerful tool for high-order data modeling, but is inherently restricted to discrete forms defined on fixed meshgrids. In this work, we propose a TR functional decomposition for both meshgrid and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Yangyang Xu , Junbo Ke , You-Wei Wen , Chao Wang

Large transformer-based language models have been shown to be very effective in many classification tasks. However, their computational complexity prevents their use in applications requiring the classification of a large set of candidates.…

Computation and Language · Computer Science 2020-05-08 Luca Soldaini , Alessandro Moschitti

Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent independent modeling of structural and semantic dependencies.…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Jiashu Liao , Pietro Liò , Marc de Kamps , Duygu Sarikaya

The advent of Transformer-based models has surpassed the barriers of text. When working with speech, we must face a problem: the sequence length of an audio input is not suitable for the Transformer. To bypass this problem, a usual approach…

Computation and Language · Computer Science 2021-07-08 Belen Alastruey , Gerard I. Gállego , Marta R. Costa-jussà

Pruning assumes a subnetwork exists in the original deep neural network, which can achieve comparative model performance with less computation than the original. However, it is unclear how the model performance varies with the different…

Machine Learning · Computer Science 2025-03-07 Mingxue Xu , Lisa Alazraki , Danilo P. Mandic

We present an incremental, scalable and efficient dimension reduction technique for tensors that is based on sparse random linear coding. Data is stored in a compactified representation with fixed size, which makes memory requirements low…

Data Structures and Algorithms · Computer Science 2017-03-16 Fredrik Sandin , Blerim Emruli , Magnus Sahlgren

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa…

Computation and Language · Computer Science 2020-10-13 Prafull Prakash , Saurabh Kumar Shashidhar , Wenlong Zhao , Subendhu Rongali , Haidar Khan , Michael Kayser

The integration of structured hierarchical embeddings into transformer-based architectures introduces a refined approach to lexical representation, ensuring that multi-scale semantic relationships are preserved without compromising…

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

Computation and Language · Computer Science 2021-02-17 Shengjie Luo , Kaiyuan Gao , Shuxin Zheng , Guolin Ke , Di He , Liwei Wang , Tie-Yan Liu

Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-20 Teresa Dorszewski , Albert Kjøller Jacobsen , Lenka Tětková , Lars Kai Hansen

We introduce a self-supervised speech pre-training method called TERA, which stands for Transformer Encoder Representations from Alteration. Recent approaches often learn by using a single auxiliary task like contrastive prediction,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-05 Andy T. Liu , Shang-Wen Li , Hung-yi Lee

Tensors provide a structured representation for multidimensional data, yet discretization can obscure important information when such data originates from continuous processes. We address this limitation by introducing a functional Tucker…

Machine Learning · Statistics 2026-03-27 Noah Steidle , Joppe De Jonghe , Mariya Ishteva

Machine learning and data mining algorithms are becoming increasingly important in analyzing large volume, multi-relational and multi--modal datasets, which are often conveniently represented as multiway arrays or tensors. It is therefore…

Numerical Analysis · Computer Science 2017-09-12 A. Cichocki , N. Lee , I. V. Oseledets , A. -H. Phan , Q. Zhao , D. Mandic

The widespread use of multi-sensor technology and the emergence of big datasets has highlighted the limitations of standard flat-view matrix models and the necessity to move towards more versatile data analysis tools. We show that…

Numerical Analysis · Computer Science 2015-06-19 A. Cichocki , D. Mandic , A-H. Phan , C. Caiafa , G. Zhou , Q. Zhao , L. De Lathauwer

Deep networks can be trained to map images into a low-dimensional latent space. In many cases, different images in a collection are articulated versions of one another; for example, same object with different lighting, background, or pose.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Rakib Hyder , M. Salman Asif

Time series forecasting is a crucial challenge with significant applications in areas such as weather prediction, stock market analysis, and scientific simulations. This paper introduces an embedded decomposed transformer, 'EDformer', for…

Machine Learning · Computer Science 2024-12-18 Sanjay Chakraborty , Ibrahim Delibasoglu , Fredrik Heintz