A Scalable AutoML Approach Based on Graph Neural Networks
Summary: KGpip: scalable AutoML meta-learning using graph neural networks. Constructs a dataset-pipeline graph DB by mining scripts, uses content embeddings to find similar datasets, and frames AutoML pipeline generation as graph generation; outperforms SOTA on 121 datasets. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Mossad Helali (Concordia University)
- 2. Essam Mansour (Concordia University)
- 3. Ibrahim Abdelaziz (International Business Machines T.J. Watson Research Center)
- 4. Julian Dolby (International Business Machines T.J. Watson Research Center)
- 5. Kavitha Srinivas (International Business Machines T.J. Watson Research Center)
BibTeX Citation
@article{helali_vldb22,
title = {{A Scalable AutoML Approach Based on Graph Neural Networks}},
author = {Helali, Mossad and Mansour, Essam and Abdelaziz, Ibrahim and Dolby, Julian and Srinivas, Kavitha},
journal = {PVLDB},
series = {{VLDB} '22},
volume = {15},
number = {11},
pages = {2428--2436},
doi = {10.14778/3551793.3551804},
url = {https://doi.org/10.14778/3551793.3551804},
year = {2022}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 7,127 | SubStrat: A Subset-Based Optimization Strategy for Faster AutoML | 2023 | VLDB | 5.6957765e-05 |
| 10,882 | CatDB: Data-catalog-guided, LLM-based Generation of Data-centric ML Pipelines | 2025 | VLDB | 5.093636e-05 |
| 11,292 | FedGTA: Topology-aware Averaging for Federated Graph Learning | 2024 | VLDB | 5.093636e-05 |
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 |
|---|---|---|---|---|
| 3,012 | Oracle AutoML: A Fast and Predictive AutoML Pipeline | 2020 | VLDB | 7.8519448e-05 |
| 3,272 | VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition | 2021 | VLDB | 7.5775321e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,640 | Scalable and Efficient Full-Graph GNN Training for Large Graphs | 2023 | SIGMOD |
| 2 | 6,354 | On Data-Aware Global Explainability of Graph Neural Networks | 2023 | VLDB |
| 3 | 9,371 | Towards an Optimized GROUP BY Abstraction for Large-Scale Machine Learning | 2021 | VLDB |
| 4 | 1,004 | Democratizing Data Science through Interactive Curation of ML Pipelines | 2019 | SIGMOD |
| 5 | 6,074 | Automatic Data Acquisition for Deep Learning | 2021 | VLDB |
| 6 | 7,473 | The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development | 2020 | SIGMOD |
| 7 | 4,875 | Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search | 2021 | VLDB |
| 8 | 1,048 | AGL: A Scalable System for Industrial-purpose Graph Machine Learning | 2020 | VLDB |
| 9 | 8,177 | HAIPipe: Combining Human-generated and Machine-generated Pipelines for Data Preparation | 2023 | SIGMOD |
| 10 | 3,012 | Oracle AutoML: A Fast and Predictive AutoML Pipeline | 2020 | VLDB |