The Limits of Graph Samplers for Training Inductive Recommender Systems
Summary: Evaluates six graph samplers across three inductive GNN recommenders and datasets. Halving training data preserves accuracy while cutting training time by up to 86%, but more aggressive sampling fails; temporal-aware sampling is essential. (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. Theis E. Jendal (Aalborg University)
- 2. Matteo Lissandrini (University of Verona)
- 3. Peter Dolog (Aalborg University)
- 4. Katja Hose (Vienna University of Technology)
BibTeX Citation
@article{jendal_vldb25,
title = {{The Limits of Graph Samplers for Training Inductive Recommender Systems}},
author = {Jendal, Theis E. and Lissandrini, Matteo and Dolog, Peter and Hose, Katja},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {8},
pages = {2496--2504},
doi = {10.14778/3742728.3742743},
url = {https://doi.org/10.14778/3742728.3742743},
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 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 7,942 | Efficient and Tunable Similar Set Retrieval | 2001 | SIGMOD |
| 2 | 5,603 | Output Space Sampling for Graph Patterns | 2009 | VLDB |
| 3 | 10,804 | IncrCP: Decomposing and Orchestrating Incremental Checkpoints for Effective Recommendation Model Training | 2025 | VLDB |
| 4 | 9,782 | Inductive Attributed Community Search: to Learn Communities across Graphs | 2024 | VLDB |
| 5 | 5,433 | Supercharging Recommender Systems using Taxonomies for Learning User Purchase Behavior | 2012 | VLDB |
| 6 | 8,911 | Efficient and Provable Effective Resistance Computation on Large Graphs: an Index-based Approach | 2024 | SIGMOD |
| 7 | 7,330 | Discovering Association Rules from Big Graphs | 2022 | VLDB |
| 8 | 2,688 | Accelerating Recommendation System Training by Leveraging Popular Choices | 2022 | VLDB |
| 9 | 9,411 | Can Learned Indexes be Built Efficiently? A Deep Dive into Sampling Trade-offs | 2024 | SIGMOD |
| 10 | 398 | A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search | 2021 | VLDB |