Item Embeddings

Item embeddings are numerical representations of items (e.g., products, movies) used in recommender systems and other applications to capture item characteristics and relationships. Current research focuses on improving embedding generation through techniques like contrastive learning, graph convolutional networks, and incorporating large language models to better capture semantic relationships and mitigate issues like popularity bias and data sparsity. These advancements aim to enhance the accuracy and efficiency of recommendation systems, impacting various industries by improving user experience and business outcomes. Furthermore, research explores optimizing embedding generation for specific tasks, such as sequential recommendation and cross-domain recommendation, leading to more robust and adaptable systems.

Papers

November 3, 2024

Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential Recommendation
Mingrui Liu, Sixiao Zhang, Cheng Long
Effective Recommendation Sequential Recommendation Multi Head Attention Sequential Information Item Embeddings

October 15, 2024

Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank
Donald Loveland, Xinyi Wu, Tong Zhao, Danai Koutra, Neil Shah, Mingxuan Ju
Real World Human Understanding Visual Perspective Collaborative Filtering Item Embeddings Large Scale Recommender System Low Rank Regularization Performance Guaranteed Regularization

October 11, 2024

Personalized Item Representations in Federated Multimodal Recommendation
Zhiwei Li, Guodong Long, Jing Jiang, Chengqi Zhang
Multimodal Data Recommendation System Federated Recommendation Item Embeddings Multimodal Recommendation Item Relevance

September 30, 2024

Large Language Model Empowered Embedding Generator for Sequential Recommendation
Qidong Liu, Xian Wu, Wanyu Wang, Yejing Wang, Yuanshao Zhu, Xiangyu Zhao, Feng Tian, Yefeng Zheng
Sequential Recommendation Recommendation Performance Sequential Recommender System Synchronous Generator Item Embeddings

July 11, 2024

CADC: Encoding User-Item Interactions for Compressing Recommendation Model Training Data
Hossein Entezari Zarch, Abdulla Alshabanah, Chaoyi Jiang, Murali Annavaram
Recommendation Model Item Embeddings User Item Interaction Functional Compression User Interaction Log

May 6, 2024

Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
Nishant Yadav, Nicholas Monath, Manzil Zaheer, Rob Fergus, Andrew McCallum
Indexing Method Cross Encoder Item Embeddings CUR Decomposition NN Search

December 15, 2023

MONET: Modality-Embracing Graph Convolutional Network and Target-Aware Attention for Multimedia Recommendation
Yungi Kim, Taeri Kim, Won-Yong Shin, Sang-Wook Kim
Human Attention Graph Convolutional Network GNN Based Multimodal Feature Higher Order Network Item Embeddings Multimedia Recommendation

August 24, 2023

On the Consistency of Average Embeddings for Item Recommendation
Walid Bendada, Guillaume Salha-Galvan, Romain Hennequin, Thomas Bouabça, Tristan Cazenave
Recommender System Strong Consistency Real World Data Item Embeddings Item Recommendation

August 22, 2023

Test Time Embedding Normalization for Popularity Bias Mitigation
Dain Kim, Jinhyeok Park, Dongwoo Kim
Bias Mitigation Test Time Normalization Dictionary Recommendation Quality Item Popularity Popularity Bias Item Embeddings

August 17, 2023

A Model-Agnostic Framework for Recommendation via Interest-aware Item Embeddings
Amit Kumar Jaiswal, Yu Xiong
Effective Recommendation Recommendation Model Capsule Network Model Agnostic Item Representation Item Embeddings Interest Representation

August 15, 2023

Implicit ZCA Whitening Effects of Linear Autoencoders for Recommendation
Katsuhiko Hayashi, Kazuma Onishi
Supervised Autoencoder Effective Recommendation Item Embeddings Linear Autoencoder Adaptive Whitening

July 7, 2023

AdaptiveRec: Adaptively Construct Pairs for Contrastive Learning in Sequential Recommendation
Jaeheyoung Jeon, Jung Hyun Ryu, Jewoong Cho, Myungjoo Kang
Contrastive Learning Sequential Recommendation Sequential Recommender System Recommendation Algorithm Recommendation Scenario Item Embeddings Pair Selection

March 28, 2023

Item Graph Convolution Collaborative Filtering for Inductive Recommendations
Edoardo D'Amico, Khalil Muhammad, Elias Tragos, Barry Smyth, Neil Hurley, Aonghus Lawlor
Item Embeddings User Item Interaction Bipartite Network

February 9, 2023

Adap-$\tau$: Adaptively Modulating Embedding Magnitude for Recommendation
Jiawei Chen, Junkang Wu, Jiancan Wu, Sheng Zhou, Xuezhi Cao, Xiangnan He
Recommender System Jina Embeddings Effective Recommendation Normalization Dictionary Earthquake Magnitude Item Embeddings Embedding Based

November 11, 2022

Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation
Haolun Wu, Yingxue Zhang, Chen Ma, Wei Guo, Ruiming Tang, Xue Liu, Mark Coates
Self Supervised Learning Recommendation System Contrastive Alignment Noisy Pair Item Embeddings User Embeddings Tag Aware Recommendation

July 2, 2022

GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce
Chao Yang, Ru He, Fangquan Lin, Suoyuan Song, Jingqiao Zhang, Cheng Yang
Jina Embeddings Mixture Component BERT Model Individual Representation E Commerce Multi Modal Data General Text Item Embeddings Novel Representation

June 27, 2022

Knowledge-aware Neural Collective Matrix Factorization for Cross-domain Recommendation
Li Zhang, Yan Ge, Jun Ma, Jianmo Ni, Haiping Lu
Knowledge Graph Matrix Factorization Cross Domain Recommendation Item Embeddings Relational Domain

April 23, 2022

CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space
Yupeng Hou, Binbin Hu, Zhiqiang Zhang, Wayne Xin Zhao
Effective Recommendation Session Based Recommendation Complex ECC Core Input Embeddings Item Embeddings Consistent Representation Consistent Representation Learning

April 5, 2022

MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
Jun Hu, Bryan Hooi, Shengsheng Qian, Quan Fang, Changsheng Xu
Graph Neural Network GNN Based Graph Diffusion Network Representation Item Embeddings Neural Collaborative Filtering Graph Collaborative Filtering

March 18, 2022

SiMCa: Sinkhorn Matrix Factorization with Capacity Constraints
Eric Daoud, Luca Ganassali, Antoine Baker, Marc Lelarge
Latent Space Matrix Factorization Recommendation Algorithm Sinkhorn Algorithm Item Embeddings Capacity Constraint

Item Embeddings

Papers

Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential Recommendation

Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank

Personalized Item Representations in Federated Multimodal Recommendation

Large Language Model Empowered Embedding Generator for Sequential Recommendation

CADC: Encoding User-Item Interactions for Compressing Recommendation Model Training Data

Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders

MONET: Modality-Embracing Graph Convolutional Network and Target-Aware Attention for Multimedia Recommendation

On the Consistency of Average Embeddings for Item Recommendation

Test Time Embedding Normalization for Popularity Bias Mitigation

A Model-Agnostic Framework for Recommendation via Interest-aware Item Embeddings

Implicit ZCA Whitening Effects of Linear Autoencoders for Recommendation

AdaptiveRec: Adaptively Construct Pairs for Contrastive Learning in Sequential Recommendation

Item Graph Convolution Collaborative Filtering for Inductive Recommendations

Adap-$\tau$: Adaptively Modulating Embedding Magnitude for Recommendation

Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation

GUIM -- General User and Item Embedding with Mixture of Representation in E-commerce

Knowledge-aware Neural Collective Matrix Factorization for Cross-domain Recommendation

CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space

MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering

SiMCa: Sinkhorn Matrix Factorization with Capacity Constraints