Adversarial Heterogeneous Graph Neural Network for Robust Recommendation
Bibliographic Data
| ID | 22107888 |
|---|---|
| Authors | Lei Sang (0009-0007-1480-6522, Anhui University), Min Xu (0000-0002-8940-1614, University of Technology Sydney), Shengsheng Qian (0000-0001-9488-2208, Chinese Academy of Sciences), Xindong Wu (0000-0003-2396-1704, Hefei University of Technology) |
| Year | 2023 |
| Volume | 10 |
| Issue | 5 |
| Pages | 2660-2671 |
| Publication date | 2023-10-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | IEEE Transactions on Computational Social Systems (JOURNAL) |
| Journal identifiers | ISSN: 2329-924X • E-ISSN: 2373-7476 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) (PUBLISHER) |
| DOI | 10.1109/tcss.2023.3268683 |
| OpenAlex | W4376851389 |
| Language | EN |
| Citations received | 6 |
| References cited | 47 |
Recommendation systems play a vital role in identifying the hidden interactions between users and items in online social networks. Recently, graph neural networks (GNNs) have exhibited significant performance gains by modeling the information propagation process in graph-structured data for a recommendation. However, existing GNN-based methods do not have broad applicability to heterogeneous graphs that integrate auxiliary data with diverse types. Moreover, graph structures are susceptible to noise and even unnoticed malicious perturbations, as perturbations from connected nodes can create cumulative effects on a target node in the graph. To enhance the robustness and generalization of GNN-based recommendations, we propose a new optimization model named Adversarial Heterogeneous Graph Neural Network for RECommendation (AHGNNRec). First, AHGNNRec learns user and item embeddings by exploring the distinct contributions of various types of interactions between users and items using a hierarchical heterogeneous graph neural network (HGNN). Second, to produce more robust embeddings for recommendations, we employ the adversarial training (AT) method to optimize the HGNN layers. AT is a min-max optimization training process where the generated adversarial fake nodes from normal nodes with intentional perturbations try to maximally deteriorate the recommendation performance. Following this, we learn about these adversarial user or item nodes by minimizing the impact of an additional regularization term for the recommendation. The experimental outcomes on two real-world benchmark datasets demonstrate the effectiveness of AHGNNRec
Adversarial system · Artificial neural network · Data mining · Graph · Machine learning · Recommender system · Advanced Graph Neural Networks · Computer Science · Privacy-Preserving Technologies in Data · Recommender Systems and Techniques · Artificial Intelligence · Theoretical Computer Science
Heterogeneous Propagation-Based Recommendation Systems with Knowledge Graph Attention Network
Node Injection Attack Based on Label Propagation Against Graph Neural Network
Heterogeneous Neighborhood-Enhanced Graph Contrastive Learning for Recommendation
Optimizing Feature Interaction via Information Bottleneck for CTR Prediction
An Improved Random Walk Restart Algorithm for Multisimilarity Enhanced Academic Recommendation Systems
Indirect Interactions Discovering and True Negative Sampling for Multimodal Recommendation
Neural Graph Collaborative Filtering
LightGCN
Robust Collaborative Filtering Recommendation With User-Item-Trust Records
Link Prediction Adversarial Attack Via Iterative Gradient Attack
Smoothing Adversarial Training for GNN
Detecting Group Shilling Attacks in Online Recommender Systems Based on Bisecting K-Means Clustering
Joint Multi-Grained Popularity-Aware Graph Convolution Collaborative Filtering for Recommendation
Employing Co-Learning to Evaluate the Explainability of Multimodal Sentiment Analysis
Recommendation Model Based on Enhanced Graph Convolution That Fuses Review Properties
| Unique citing works | 6 |
|---|---|
| Citations per year | 3 |
| Citation span | 2024 - 2026 (3) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 6 |