Co Occurrence Graph

Co-occurrence graphs represent relationships between items (e.g., words, products, labels) by connecting items that frequently appear together, enabling the analysis of complex relationships and patterns within large datasets. Current research focuses on leveraging these graphs within various machine learning models, including graph neural networks (GNNs), to improve tasks such as recommendation systems, text classification, and matrix completion. This approach enhances performance by incorporating relational information, addressing challenges like data sparsity and cold-start problems, and leading to more accurate and efficient algorithms in diverse applications. The resulting improvements have significant implications for various fields, including e-commerce, natural language processing, and information retrieval.

Papers

May 3, 2024

Learning label-label correlations in Extreme Multi-label Classification via Label Features
Siddhant Kharbanda, Devaansh Gupta, Erik Schultheis, Atmadeep Banerjee, Cho-Jui Hsieh, Rohit Babbar
LeArning Abstract Label Correlation Extreme Multi Label Co Occurrence Graph Soft Target

October 30, 2023

LightSAGE: Graph Neural Networks for Large Scale Item Retrieval in Shopee's Advertisement Recommendation
Dang Minh Nguyen, Chenfei Wang, Yan Shen, Yifan Zeng
Graph Neural Network Recommendation System Product Retrieval Large Scale Retrieval Co Occurrence Graph

October 22, 2023

Item-Graph2vec: a Efficient and Effective Approach using Item Co-occurrence Graph Embedding for Collaborative Filtering
Ruilin Yuan, Leya Li, Yuanzhe Cai
Collaborative Filtering Effective Approach Co Occurrence Graph Novel Zero Shot Item2Vec Framework

July 5, 2023

Graph Contrastive Topic Model
Zheheng Luo, Lei Liu, Qianqian Xie, Sophia Ananiadou
Contrastive Learning Topic Embeddings Co Occurrence Graph

January 11, 2023

Word-Graph2vec: An efficient word embedding approach on word co-occurrence graph using random walk technique
Wenting Li, Jiahong Xue, Xi Zhang, Huacan Chen, Zeyu Chen, Feijuan Huang, Yuanzhe Cai
High Efficiency Constructive Approach Random Walk Word Usage Graph Co Occurrence Graph

August 4, 2022

Semantic Interleaving Global Channel Attention for Multilabel Remote Sensing Image Classification
Yongkun Liu, Kesong Ni, Yuhan Zhang, Lijian Zhou, Kun Zhao
Remote Sensing Image Channel Attention Label Correlation Co Occurrence Graph

February 6, 2022

Triangle Graph Interest Network for Click-through Rate Prediction
Wensen Jiang, Yizhu Jiao, Qingqin Wang, Chuanming Liang, Lijie Guo, Yao Zhang, Zhijun Sun, Yun Xiong, Yangyong Zhu
Click Through Rate Prediction User Interest Interest Network Co Occurrence Graph

January 29, 2022

Modeling Complex Dependencies for Session-based Recommendations via Graph Neural Networks
Qian Zhang, Wenpeng Lu
Graph Neural Network Session Based Recommendation Item Representation Recommendation Scenario Downstream Forecasting Task Session Based Dependency Modeling Co Occurrence Graph

January 2, 2022

Matrix Completion with Hierarchical Graph Side Information
Adel Elmahdy, Junhyung Ahn, Changho Suh, Soheil Mohajer
Matrix Completion Graph Clustering Rating Matrix Co Occurrence Graph Graph Side Information

December 13, 2021

Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification
Yinhua Piao, Sangseon Lee, Dohoon Lee, Sun Kim
Graph Neural Network Sparse Structure Document Classification Graph Level Classification Document Graph Co Occurrence Graph Document Categorization

Co Occurrence Graph

Papers

Learning label-label correlations in Extreme Multi-label Classification via Label Features

LightSAGE: Graph Neural Networks for Large Scale Item Retrieval in Shopee's Advertisement Recommendation

Item-Graph2vec: a Efficient and Effective Approach using Item Co-occurrence Graph Embedding for Collaborative Filtering

Graph Contrastive Topic Model

Word-Graph2vec: An efficient word embedding approach on word co-occurrence graph using random walk technique

Semantic Interleaving Global Channel Attention for Multilabel Remote Sensing Image Classification

Triangle Graph Interest Network for Click-through Rate Prediction

Modeling Complex Dependencies for Session-based Recommendations via Graph Neural Networks

Matrix Completion with Hierarchical Graph Side Information

Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification