Learning Image and User Features for Recommendation in Social Networks

By Xue Geng, Hanwang Zhang, Jingwen Bian, Tat-seng Chua. 2015

227 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Yongfeng Zhang
5. Liqiang Nie
6. Hanwang Zhang
7. Xu Chen
8. Meng Wang

In Information Systems

1. Xiangnan He
2. Tat-seng Chua
3. Xiang Wang
4. Yongfeng Zhang
5. Xu Chen
6. Liqiang Nie
7. Fuli Feng
8. Yixin Cao

Citations in the corpus

• Neural Collaborative Filtering (2017, methodology): “Since the last hidden layer of NCF determines the model capability, we term it as predictive factors and evaluated the factors of [8 , 16 , 32 , 64].”
• A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, methodology): “ChebNet graph GCN [72] Graph Convolutional Network graph GNN [120] Graph Neural Network graph [121] adapted Graph Neural Network molecules graph GGS-NNs [122] adapted Graph Neural Network graph HNE [33] CNN + FC graph with image and text DUIF [35] a hierarchical deep model social curation network Pr”
• Contrastive Learning for Cold-Start Recommendation (2021, methodology): “• DUIF [9] Different from the CF-based model, this method learns the user reference to the item’s features without modeling the CF signal, which intrinsically avoids the cold-start problem.”
• Adversarial Personalized Ranking for Recommendation (2018, methodology): “This implicit feedback dataset was originally constructed by [13] for content-based image recommendation.”
• NAIS: Neural Attentive Item Similarity Model for Recommendation (2018, unknown): “Existing works on DNNs for recommendation can be divided into two types: 1) using DNNs for feature extraction from auxiliary data, e.g., images and texts [38], [39], and 2) using DNNs for learning the user-item scoring function [5], [40], [41].”
• Fast Matrix Factorization for Online Recommendation with Implicit Feedback (2016, methodology): “To make our method more applicable to real-world settings, we plan to encode side information such as user social contexts [8] and reviews [9] by extending eALS to more generic models, such as collective factorization [11] and Factorization machines [26].”
• Visually Explainable Recommendation (2018, methodology): “…product style analysis and recommendation; He et al [8] further extended the approach to pair-wise learning to rank for recommendation; Geng et al [6] adopted image features for recommendation in a social network setting; and Wang et al [31] extracted image features with neural network for…”
• Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention (2017, methodology): “[15] for evaluating image recommendation.”
• Neural Collaborative Filtering vs. Matrix Factorization Revisited (2020, methodology): “dot product yields better results. 3.1 Experimental setup The NCF paper [16] evaluates on an item retrieval task on two datasets: a binarized version of Movielens 1M [13] and a dataset from Pinterest [12]. Both are implicit feedback datasets, i.e. they contain only binary positive tuples between a u”
• Mieb: Massive Image Embedding Benchmark (2025, unknown): “Image and text embeddings power a wide range of use cases, from search engines to recommendation systems [19, 23, 67].”