Local Embeddings

Local embeddings represent data points (e.g., image regions, nodes in a graph, audio segments) as low-dimensional vectors, capturing their local context and relationships within a larger dataset. Current research focuses on improving the accuracy and scalability of generating these embeddings, often employing graph autoencoders, contrastive learning, and attention mechanisms within deep learning frameworks to achieve this. These advancements are driving improvements in various applications, including image retrieval, graph analysis, music recommendation, and action recognition, by enabling more efficient and accurate processing of complex data.

Papers

October 18, 2024

On the Regularization of Learnable Embeddings for Time Series Processing
Luca Butera, Giovanni De Felice, Andrea Cini, Cesare Alippi
Deep Learning Time Series Analysis Learned Embeddings Local Embeddings

July 29, 2024

MaskInversion: Localized Embeddings via Optimization of Explainability Maps
Walid Bousselham, Sofian Chaybouti, Christian Rupprecht, Vittorio Ferrari, Hilde Kuehne
Foundation Model Optimization Purpose Vision Language Foundation Model Vision Language Alignment Explanation Map Local Embeddings Query Driven Mask Transformer Region Representation

February 2, 2024

L2G2G: a Scalable Local-to-Global Network Embedding with Graph Autoencoders
Ruikang Ouyang, Andrew Elliott, Stratis Limnios, Mihai Cucuringu, Gesine Reinert
Graph Representation Learning Potential Scalability Dense Network Graph AutoEncoder Graph Autoencoders Local Embeddings

January 17, 2024

On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations
Matthew C. McCallum, Matthew E. P. Davies, Florian Henkel, Jaehun Kim, Samuel E. Sandberg
Contrastive Learning Data Augmentation Mixed Effect Audio Representation Music Representation Audio Embeddings Music Datasets Local Embeddings

November 7, 2023

Deep Hashing via Householder Quantization
Lucas R. Schwengber, Lucas Resende, Paulo Orenstein, Roberto I. Oliveira
Quantization Technique Deep Hashing Local Embeddings Low Rank Quantization

October 1, 2023

Self-supervised Learning of Contextualized Local Visual Embeddings
Thalles Santos Silva, Helio Pedrini, Adín Ramírez Rivera
Self Supervised Learning Self Supervised Contextual Embeddings Dense Prediction Task Local Embeddings

January 27, 2023

SplitGNN: Splitting GNN for Node Classification with Heterogeneous Attention
Xiaolong Xu, Lingjuan Lyu, Yihong Dong, Yicheng Lu, Weiqiang Wang, Hong Jin
Neural Network Node Classification Node Embeddings Global Embeddings Heterogeneous Attention Local Embeddings

September 21, 2022

Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition
Anqi Zhu, Qiuhong Ke, Mingming Gong, James Bailey
Skeleton Based Action Recognition One Shot Skeleton Representation Adaptive Graph Shot Meta Learning Local Embeddings

June 18, 2022

Secure Embedding Aggregation for Federated Representation Learning
Jiaxiang Tang, Jinbao Zhu, Songze Li, Lichao Sun
Jina Embeddings Private Data Data Aggregation Secure Approach Representation Learning Framework Local Embeddings Federated Representation Learning

November 28, 2021

ExCon: Explanation-driven Supervised Contrastive Learning for Image Classification
Zhibo Zhang, Jongseong Jang, Chiheb Trabelsi, Ruiwen Li, Scott Sanner, Yeonjeong Jeong, Dongsub Shim
Contrastive Learning Image Classification Saliency Explanation Image Data Augmentation Contrastive Augmentation Local Embeddings