Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation
Summary: Lighter-X decouples propagation and compresses adjacency and embeddings in graph recommenders, reducing parameters from O(nd) to O(hd), h≪n. Plug-and-play integration preserves performance, with better results using just 1% of LightGCN’s parameters on large graphs. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yanping Zheng (Renmin University of China)
- 2. Zhewei Wei (Renmin University of China)
- 3. Frank de Hoog (Commonwealth Scientific and Industrial Research Organisation; Data 61)
- 4. Xu Chen (Renmin University of China)
- 5. Hongteng Xu (Renmin University of China)
- 6. Yuhang Ye (Huawei)
- 7. Jiadeng Huang (Huawei)
BibTeX Citation
@article{zheng_vldb25,
title = {{Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation}},
author = {Zheng, Yanping and Wei, Zhewei and de Hoog, Frank and Chen, Xu and Xu, Hongteng and Ye, Yuhang and Huang, Jiadeng},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {11},
pages = {3721--3729},
doi = {10.14778/3749646.3749649},
url = {https://doi.org/10.14778/3749646.3749649},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 2 of 2 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 2,688 | Accelerating Recommendation System Training by Leveraging Popular Choices | 2022 | VLDB | 8.2564305e-05 |
| 5,596 | Efficient Tree-SVD for Subset Node Embedding over Large Dynamic Graphs | 2023 | SIGMOD | 6.1548101e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,980 | Decoupled Graph Neural Networks for Large Dynamic Graphs | 2023 | VLDB |
| 2 | 1,863 | ByteGNN: Efficient Graph Neural Network Training at Large Scale | 2022 | VLDB |
| 3 | 2,383 | ICS-GNN: Lightweight Interactive Community Search via Graph Neural Network | 2021 | VLDB |
| 4 | 11,464 | EmbedX: A Versatile, Efficient and Scalable Platform to Embed Both Graphs and High-Dimensional Sparse Data | 2023 | VLDB |
| 5 | 2,640 | Scalable and Efficient Full-Graph GNN Training for Large Graphs | 2023 | SIGMOD |
| 6 | 13,321 | The Limits of Graph Samplers for Training Inductive Recommender Systems | 2025 | VLDB |
| 7 | 9,554 | Explaining GNN-based Recommendations in Logic | 2025 | VLDB |
| 8 | 4,600 | LightNE: A Lightweight Graph Processing System for Network Embedding | 2021 | SIGMOD |
| 9 | 2,688 | Accelerating Recommendation System Training by Leveraging Popular Choices | 2022 | VLDB |
| 10 | 13,356 | LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning | 2024 | VLDB |