UvA-DARE ( Digital Academic Repository ) Graph Convolutional Matrix Completion

By Rianne van den Berg, Thomas Kipf, Max Welling. 2017

How researchers see this paper

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

In Graph Learning

Citations in the corpus

Stochastic Training of Graph Convolutional Networks (2017, methodology): “…node classification (Kipf & Welling, 2017), inductive node embedding (Hamilton et al., 2017a), link prediction (Kipf & Welling, 2016; Berg et al., 2017) and knowledge graphs (Schlichtkrull et al., 2017), outperforming multi-layer perceptron (MLP) models that do not use the graph…”
Graph Convolutional Neural Networks for Web-Scale Recommender Systems (2018, background): “, to exploit user-to-item interaction graphs as well as social graphs) [6, 19, 21, 24, 29, 30].”
Compositional Fairness Constraints for Graph Embeddings (2019, methodology): “Following Berg et al. (2017) we treat this recommendation task as an edge prediction problem between users and movies, viewing the different possible ratings as different edge relations.”
Representation Learning on Graphs: Methods and Applications (2017, background): “There are a number of recent approaches that follow the basic procedure outlined in Algorithm 1, including graph convolutional networks (GCN) [34, 35, 52, 55], column networks [49], and the GraphSAGE algo-rithm [28].”
Attention-based Graph Neural Network for Semi-supervised Learning (2018, methodology): “There are several extensions to this model as discussed in the previous section, but this standard graph neural network has proved powerful in several problems over graphs, e.g. [9, 6, 14].”
Sequential Recommendation with Graph Neural Networks (2021, methodology): “to factorizing user-item rating matrices into user and item embedding matrices for recommendation [2] and Wang et al.”
Knowledge Graph Contrastive Learning for Recommendation (2022, unknown): “• GC-MC [1].”
Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach (2020, methodology): “Besides, in order to better verify the effectiveness of the linear and the residual learning part, we design two variants of the GC-MC: L inear-GC-MC (L-GC-MC), and R esudial-GC-MC (R-GC-MC), with L denotes replacing the original non-linear transformation with linear embedding propagation, and R den”
A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “Thus, a natural extension is to mine the [20], PMLAM [21], pQCF [22], FAWMF [23] User Interacted items+UID (Free Embed+Heuristic Agg) Item IID (Free Embed) SVD++ [24] User Interacted items (Free Embed+Heuristic Agg) Item IID (Free Embed) NAIS [25] User Interacted items+UID (Free Embed+Heuristic Agg)”
MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video (2019, background): “[5] treated the recommender systems as the view of link prediction on graphs and proposed a graph auto-encoder framework based on message passing on the bipartite interaction graph.”
DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation (2020, background): “Therefore, many recent works focus on the spatial based GCNs for recommendation [4], [40], [47], [48].”
A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions (2024, background): “GCNs were first introduced in “Spectral Networks and Deep Locally Connected Networks on Graphs” [34].”
Deep Models of Interactions Across Sets (2018, background): “MC (Cand`es & Recht, 2009) 0.973 GMC (Kalofolias et al., 2014) 0.996 GRALS (Rao et al., 2015) 0.945 sRGCNN (Monti et al., 2017) 0.929 Factorized EAE (ours) 0.920 GC-MC (Berg et al., 2017) 0.910 Self-Supervised Model (ours) 0.910”
A federated graph neural network framework for privacy-preserving personalization (2021, methodology): “For example, Berg et al. [2] proposed to use graph convolutional autoencoders to learn user and item representations from the user-item bipartite graph.”
A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “[8] proposed to pass neighborhood messages by summing and assign weight-sharing transformation channels for different relational edges (i.”
What graph neural networks cannot learn: depth vs width (2019, background): “In the literature, one-hot encoded node ids are occasionally useful (Kipf & Welling, 2016; Berg et al., 2017).”
Disentangled Graph Collaborative Filtering (2020, methodology): “More recent works [10, 36, 40] further organize all historical interactions as a”
Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System (2020, methodology): “Five real-world benchmark datasets are used in our experiments: ML10M is the widely-used [6, 40, 59] dataset from MovieLens with 10M movie ratings.”