Summary of Improving Graph Convolutional Networks with Transformer Layer in Social-based Items Recommendation, by Thi Linh Hoang et al.
Improving Graph Convolutional Networks with Transformer Layer in social-based items recommendation
by Thi Linh Hoang, Tuan Dung Pham, Viet Cuong Ta
First submitted to arxiv on: 12 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach improves the Graph Convolutional Network (GCN) for predicting ratings in social networks by incorporating several layers of transformer architecture. This enhanced model focuses on the encoder architecture for node embedding, leveraging the attention mechanism to rearrange the feature space and obtain more efficient embeddings for downstream tasks. The results demonstrate better performance compared to traditional GCNs on link prediction tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary We improved the Graph Convolutional Network (GCN) for predicting ratings in social networks. We added special layers to help the model understand relationships between people better. This makes it work better when trying to predict who will be friends with whom. Our new approach does a better job than the original GCN at guessing connections between people. |
Keywords
* Artificial intelligence * Attention * Convolutional network * Embedding * Encoder * Gcn * Transformer
