Spectral Embedding

Spectral embedding techniques aim to represent complex data, such as graphs or hyperspectral images, in lower-dimensional spaces while preserving essential structural information. Current research focuses on developing efficient and scalable algorithms, including those based on graph convolutional networks, random Fourier features, and neural networks, to address challenges posed by high dimensionality and large datasets. These advancements are improving performance in various applications, such as graph clustering, hyperspectral image classification, and single-cell genomics analysis, by enabling more effective data analysis and pattern recognition. Furthermore, ongoing work explores connections between spectral embedding and other machine learning paradigms, like contrastive learning and matrix completion, to enhance theoretical understanding and practical applicability.

Papers

November 3, 2024

G-SPARC: SPectral ARchitectures tackling the Cold-start problem in Graph learning
Yahel Jacobs, Reut Dayan, Uri Shaham
Graph Drawing Link Prediction Graph Representation Graph Learning Spectral Embedding Cold Start Cold Start Problem

October 26, 2024

Convergence Guarantees for the DeepWalk Embedding on Block Models
Christopher Harker, Aditya Bhaskara
Convergence Guarantee Random Walk Large Graph Graph Embeddings Stochastic Block Model Spectral Embedding Block Model

August 11, 2024

Scalable and Adaptive Spectral Embedding for Attributed Graph Clustering
Yunhui Liu, Tieke He, Qing Wu, Tao Zheng, Jianhua Zhao
Potential Scalability Graph Convolution Spectral Clustering Spectral Feature Large Graph Graph Clustering Spectral Embedding

July 9, 2024

HTD-Mamba: Efficient Hyperspectral Target Detection with Pyramid State Space Model
Dunbin Shen, Xuanbing Zhu, Jiacheng Tian, Jianjun Liu, Zhenrong Du, Hongyu Wang, Xiaorui Ma
Spectral Embedding Intrinsic Feature Spectral Augmentation Hyperspectral Target Detection

July 2, 2024

Spectral Graph Reasoning Network for Hyperspectral Image Classification
Huiling Wang
Hyperspectral Image Classification Spectral Graph Neural Network Spectral Information Spectral Embedding

May 20, 2024

Kernel spectral joint embeddings for high-dimensional noisy datasets using duo-landmark integral operators
Xiucai Ding, Rong Ma
Kernel Hilbert Space Single Cell Kernel Extension Spectral Embedding Single Cell Multi Omics Integral Operator High Dimensional Noisy

March 13, 2024

When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?
Gautham Govind Anil, Pascal Esser, Debarghya Ghoshdastidar
Contrastive Learning Neural Tangent Kernel Principal Component Analysis Spectral Embedding Contrastive Model

February 6, 2024

Edge-Parallel Graph Encoder Embedding
Ariel Lubonja, Cencheng Shen, Carey Priebe, Randal Burns
Graph Drawing Low Dimensional Representation Graph Encoder Spectral Embedding Neural Graph

November 26, 2023

A Novel Normalized-Cut Solver with Nearest Neighbor Hierarchical Initialization
Feiping Nie, Jitao Lu, Danyang Wu, Rong Wang, Xuelong Li
Spectral Clustering Spectral Embedding Normalized Cut

October 28, 2023

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding
Jiangyan Ma, Yifei Wang, Yisen Wang
Graph Transformer Spectral Embedding Cultural Sign Laplacian Canonization

July 25, 2023

Gradient-Based Spectral Embeddings of Random Dot Product Graphs
Marcelo Fiori, Bernardo Marenco, Federico Larroca, Paola Bermolen, Gonzalo Mateos
Graph Representation Learning Spectral Embedding Random Dot Product Graph

May 31, 2023

Spectal Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning
Marina Munkhoeva, Ivan Oseledets
Self Supervised Learning Inductive Bias Self Supervised Method Matrix Completion Low Rank Matrix Completion Spectral Embedding Harmonic Sound Self Supervised Representation Learning Method

May 28, 2023

Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation
Edoardo D'Amico, Aonghus Lawlor, Neil Hurley
Graph Convolution Item Representation Spectral Embedding Top N Recommendation

May 14, 2023

Learning Structure Aware Deep Spectral Embedding
Hira Yaseen, Arif Mahmood
Spectral Embedding Deep Spectral Self Expressive

April 6, 2023

Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation
Zhijie Deng, Yucen Luo
Spectral Clustering Unsupervised Semantic Segmentation Spectral Embedding Neural Eigenfunctions

February 20, 2023

Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head
Randall Balestriero
Self Supervised Learning Generative Modeling Unsupervised Learning Self Supervision Spectral Embedding Decoder Architecture

February 6, 2023

Root Laplacian Eigenmaps with their application in spectral embedding
Shouvik Datta Choudhury
Application Proficiency Riemannian Manifold Graph Signal Processing Graph Laplacian Spectral Embedding Laplacian Eigenmaps Laplacian Canonization Laplacian Operator

November 30, 2022

BASiS: Batch Aligned Spectral Embedding Space
Or Streicher, Ido Cohen, Guy Gilboa
Deep Space Dimensional Embeddings Spectral Graph Alternative Basis Spectral Embedding Batch Learning Spectral Normalization

August 20, 2022

Adversarial contamination of networks in the setting of vertex nomination: a new trimming method
Sheyda Peyman, Minh Tang, Vince Lyzinski
Network Programming Graph Data Goal Vertex Spectral Embedding Graph Inference Writer Independent Setting

July 22, 2022

A flexible PageRank-based graph embedding framework closely related to spectral eigenvector embeddings
Disha Shur, Yufan Huang, David F. Gleich
New Framework Graph Drawing Jina Embeddings Spectral Embedding Personalized Pagerank PageRank Algorithm

Spectral Embedding

Papers

G-SPARC: SPectral ARchitectures tackling the Cold-start problem in Graph learning

Convergence Guarantees for the DeepWalk Embedding on Block Models

Scalable and Adaptive Spectral Embedding for Attributed Graph Clustering

HTD-Mamba: Efficient Hyperspectral Target Detection with Pyramid State Space Model

Spectral Graph Reasoning Network for Hyperspectral Image Classification

Kernel spectral joint embeddings for high-dimensional noisy datasets using duo-landmark integral operators

When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?

Edge-Parallel Graph Encoder Embedding

A Novel Normalized-Cut Solver with Nearest Neighbor Hierarchical Initialization

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

Gradient-Based Spectral Embeddings of Random Dot Product Graphs

Spectal Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning

Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation

Learning Structure Aware Deep Spectral Embedding

Learning Neural Eigenfunctions for Unsupervised Semantic Segmentation

Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head

Root Laplacian Eigenmaps with their application in spectral embedding

BASiS: Batch Aligned Spectral Embedding Space

Adversarial contamination of networks in the setting of vertex nomination: a new trimming method

A flexible PageRank-based graph embedding framework closely related to spectral eigenvector embeddings