paper-with-me

Papers

Transformer-based dimensionality reduction

2022-10-15 · Ruisheng Ran, Tianyu Gao, Bin Fang

Recently, Transformer is much popular and plays an important role in the fields of Machine Learning (ML), Natural Language Processing (NLP), and Computer Vision (CV), etc. In this paper, based on the Vision Transformer (ViT) model, a new dimensionality reduction (DR) model is proposed, named Transformer-DR. From data visualization, image reconstruction and face recognition, the representation ability of Transformer-DR after dimensionality reduction is studied, and it is compared with some representative DR methods to understand the difference between Transformer-DR and existing DR methods. The experimental results show that Transformer-DR is an effective dimensionality reduction method.

📄 PDF Abstract BibTeX arXiv:2210.08288

Code (0)

등록된 구현이 없습니다.

Tasks

Data VisualizationDimensionality ReductionFace RecognitionImage Reconstruction

Methods 이 논문이 사용한 방법론

Attention 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…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Exploring the Influence of Dimensionality Reduction on Anomaly Detection Performance in Multivariate Time Series

2024-03-07 · Mahsun Altın, Altan Cakir

This paper presents an extensive empirical study on the integration of dimensionality reduction techniques with advanced unsupervised time series anomaly detection models, focusing on the MUTANT and Anomaly-Transformer m…

Anomaly DetectionDimensionality ReductionTime SeriesTime Series Analysis+1

Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality

2021-05-07 · NAACL 2021 4 · Adithya V Ganesan, Matthew Matero, Aravind Reddy Ravula, Huy Vu 외

In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-base…

Dimensionality Reduction

Dimensionality Reduction in Sentence Transformer Vector Databases with Fast Fourier Transform

2024-04-09 · Vitaly Bulgakov, Alec Segal

Dimensionality reduction in vector databases is pivotal for streamlining AI data management, enabling efficient storage, faster computation, and improved model performance. This paper explores the benefits of reducing ve…

Computational EfficiencyDimensionality ReductionManagementRAG+4

DimenFix: A novel meta-dimensionality reduction method for feature preservation

2022-11-30 · Qiaodan Luo, Leonardo Christino, Fernando V Paulovich, Evangelos Milios

Dimensionality reduction has become an important research topic as demand for interpreting high-dimensional datasets has been increasing rapidly in recent years. There have been many dimensionality reduction methods with…

Dimensionality Reduction

On Geodesic Distances and Contextual Embedding Compression for Text Classification

2021-04-22 · NAACL (TextGraphs) 2021 6 · Rishi Jha, Kai Mihata

In some memory-constrained settings like IoT devices and over-the-network data pipelines, it can be advantageous to have smaller contextual embeddings. We investigate the efficacy of projecting contextual embedding data …

ClassificationDimensionality ReductionGeneral Classificationtext-classification+1