Feature Space

Feature space, a vector representation of data, is central to machine learning, aiming to capture meaningful relationships between data points for improved model performance and interpretability. Current research focuses on optimizing feature space construction through techniques like optimal transport, autoencoders, and large language models, often incorporating multi-scale embeddings and attention mechanisms to enhance representation quality. These advancements are impacting various fields, improving the accuracy and efficiency of tasks ranging from image classification and anomaly detection to robot personalization and clinical decision-making. The development of robust and interpretable feature spaces is crucial for advancing machine learning's capabilities and trustworthiness across diverse applications.

Papers

December 27, 2022

Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents
Meng Xiao, Dongjie Wang, Min Wu, Ziyue Qiao, Pengfei Wang, Kunpeng Liu, Yuanchun Zhou, Yanjie Fu
Actor Critic Feature Space Feature Transformation Feature Generation

November 17, 2022

FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data
Tailin Zhou, Jun Zhang, Danny H. K. Tsang
Simple Classifier Heterogeneous Data Feature Space Feature Alignment Visual Information Anchor Data Divergence

November 10, 2022

Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization
Tingyu Wang, Zhedong Zheng, Zunjie Zhu, Yuhan Gao, Yi Yang, Chenggang Yan
Feature Space Cross View Feature Decorrelation Effective Regularization Cross View Geo Localization Multi View Sampling

November 7, 2022

Towards a mathematical understanding of learning from few examples with nonlinear feature maps
Oliver J. Sutton, Alexander N. Gorban, Ivan Y. Tyukin
Feature Space AI Model Fewer Example Feature Transformation Mathematical Understanding

November 1, 2022

Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces
Ashish Tiwari, Sresth Tosniwal, Shanmuganathan Raman
Graph Representation Heterogeneous Graph Node Representation Feature Space Semi Supervised Node Classification Graph Convolution Network Topological Representation

October 28, 2022

Latent Space is Feature Space: Regularization Term for GANs Training on Limited Dataset
Pengwei Wang
Generative Adversarial Network Latent Space GAN Model Limited Data Feature Space GAN Training GAN Based Regularization Term

October 26, 2022

A Sign That Spells: DALL-E 2, Invisual Images and The Racial Politics of Feature Space
Fabian Offert, Thao Phan
Feature Space Cultural Sign Salient Concept Visual Culture

October 14, 2022

FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning
Rui Ye, Zhenyang Ni, Chenxin Xu, Jianyu Wang, Siheng Chen, Yonina C. Eldar
Data Heterogeneity Feature Space

October 13, 2022

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces
Qing Li, Yu-Shen Liu, Jin-San Cheng, Cheng Wang, Yi Fang, Zhizhong Han
3D Point Cloud Feature Space Normal Estimation Synthetic Shape

September 16, 2022

Self-Optimizing Feature Transformation
Meng Xiao, Dongjie Wang, Min Wu, Kunpeng Liu, Hui Xiong, Yuanchun Zhou, Yanjie Fu
Feature Space Model Generalization Feature Engineering Feature Transformation Optimal Representation

September 7, 2022

Bayesian learning of feature spaces for multitasks problems
Carlos Sevilla-Salcedo, Ascensión Gallardo-Antolín, Vanessa Gómez-Verdejo, Emilio Parrado-Hernández
Multi Task Feature Space Radial Basis Function Bayesian Learning Extreme Learning Machine

August 31, 2022

Injecting Image Details into CLIP's Feature Space
Zilun Zhang, Cuifeng Shen, Yuan Shen, Huixin Xiong, Xinyu Zhou
Vision Language Model Single CLIP Synthetic Dataset Feature Space Joint Representation Single Vector Representation Image Specific Information

August 19, 2022

Demystifying Randomly Initialized Networks for Evaluating Generative Models
Junghyuk Lee, Jun-Hyuk Kim, Jong-Seok Lee
Convolutional Neural Network Generative Model Network Programming Feature Space Random Feature Random Network Randomness Factor

August 5, 2022

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space
Xingran Liao, Baoliang Chen, Hanwei Zhu, Shiqi Wang, Mingliang Zhou, Sam Kwong
Image Quality Wasserstein Distance Feature Space Nr Iqa Quality Prediction Document Degradation Perceptual Space

August 3, 2022

Centroids Matching: an efficient Continual Learning approach operating in the embedding space
Jary Pomponi, Simone Scardapane, Aurelio Uncini
Catastrophic Forgetting Incremental Learning Deep Space Feature Space Accuracy Improvement Efficient Continual Learning Feature Centroid Novel Regularization

July 18, 2022

ManiFeSt: Manifold-based Feature Selection for Small Data Sets
David Cohen, Tal Shnitzer, Yuval Kluger, Ronen Talmon
Feature Selection Feature Space Small Datasets Contextualized Target Representation

July 9, 2022

Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space
Amine Ouasfi, Adnane Boukhayma
Feature Space Shape Reconstruction Signed Distance Function Input Point Cloud Implicit Shape Sparse Point Cloud Level Set Implicit Reconstruction

July 2, 2022

Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces
Alexander Thebelt, Calvin Tsay, Robert M. Lee, Nathan Sudermann-Merx, David Walz, Behrang Shafei, Ruth Misener
Neural Architecture Search Bayesian Optimization Participation Constraint Black Box Optimization Feature Space Tree Ensemble Ensemble Kernel

June 21, 2022

Feature Space

Papers

Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents

FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data

Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization

Towards a mathematical understanding of learning from few examples with nonlinear feature maps

Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces

Latent Space is Feature Space: Regularization Term for GANs Training on Limited Dataset

A Sign That Spells: DALL-E 2, Invisual Images and The Racial Politics of Feature Space

FedFM: Anchor-based Feature Matching for Data Heterogeneity in Federated Learning

HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces

Self-Optimizing Feature Transformation

Bayesian learning of feature spaces for multitasks problems

Injecting Image Details into CLIP's Feature Space

Demystifying Randomly Initialized Networks for Evaluating Generative Models

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space

Centroids Matching: an efficient Continual Learning approach operating in the embedding space

ManiFeSt: Manifold-based Feature Selection for Small Data Sets

Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space

Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spaces

BiometricBlender: Ultra-high dimensional, multi-class synthetic data generator to imitate biometric feature space

Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion Recognition