paper-with-me

Papers

Partial Tensorized Transformers for Natural Language Processing

2023-10-30 · Subhadra Vadlamannati, Ryan Solgi

The transformer architecture has revolutionized Natural Language Processing (NLP) and other machine-learning tasks, due to its unprecedented accuracy. However, their extensive memory and parameter requirements often hinder their practical applications. In this work, we study the effect of tensor-train decomposition to improve the accuracy and compress transformer vision-language neural networks, namely BERT and ViT. We focus both on embedding-layer compression and partial tensorization of neural networks (PTNN) through an algorithmic approach. Our novel PTNN approach significantly improves the accuracy of existing models by up to 5%, all without the need for post-training adjustments, breaking new ground in the field of tensor decomposition.

📄 PDF Abstract BibTeX arXiv:2310.20077

Code (0)

등록된 구현이 없습니다.

Tasks

Tensor Decomposition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
WordPiece 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Similar Papers 제목 키워드 기반

Tensorized Embedding Layers

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova, Elena Orlova 외

The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is large, the corresponding weight matrices…

Tensorized Embedding Layers for Efficient Model Compression

2019-01-30 · Oleksii Hrinchuk, Valentin Khrulkov, Leyla Mirvakhabova, Elena Orlova 외

The embedding layers transforming input words into real vectors are the key components of deep neural networks used in natural language processing. However, when the vocabulary is large, the corresponding weight matrices…

Language ModellingMachine TranslationmodelModel Compression+1

Reducing Computational Costs in Sentiment Analysis: Tensorized Recurrent Networks vs. Recurrent Networks

2023-06-16 · Gabriel Lopez, Anna Nguyen, Joe Kaul

Anticipating audience reaction towards a certain text is integral to several facets of society ranging from politics, research, and commercial industries. Sentiment analysis (SA) is a useful natural language processing (…

Sentiment Analysis

Tensorizing Engram: Sharing Latents Across N-Gram Embeddings is Beneficial in LLMs

2026-06-06 · Wuyang Zhou, Yuxuan Gu, Giorgos Iacovides, Yuning Qiu 외 arxiv

Modern language models represent text using discrete token-level embeddings, which forces recurring multi-token patterns to be learned implicitly across Transformer layers. Both Over-tokenized Transformers and Engram att…

Structured Multidimensional Representation Learning for Large Language Models

2026-03-05 · Alaa El Ichi, Khalide Jbilou, Mohamed El Guide, Franck Dufrenois arxiv

Transformer architectures achieve state-of-the-art performance across a wide range of pattern recognition and natural language processing tasks, but their scaling is accompanied by substantial parameter growth and redund…

Representation Learning