AixelNet: A Pre-trained Model with Table-aware Adaptation for Structured Data Prediction
Summary: AixelNet: a pre-trained model for heterogeneous tabular prediction that extracts table-level meta-features and uses a multi-predictor backbone to avoid task-specific retraining. A hypernetwork dynamically composes base predictors per table, with regularizers for balanced/diverse usage and sparse updates for efficiency, improving accuracy on 40 tabular tasks versus eight SOTA baselines. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Liming Wang (Beijing Institute of Technology)
- 2. Meihui Zhang (Beijing Institute of Technology)
- 3. Zhaojing Luo (Beijing Institute of Technology)
BibTeX Citation
@inproceedings{wang_sigmod26,
title = {{AixelNet: A Pre-trained Model with Table-aware Adaptation for Structured Data Prediction}},
author = {Wang, Liming and Zhang, Meihui and Luo, Zhaojing},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769814},
url = {https://dl.acm.org/doi/10.1145/3769814},
year = {2026}
}
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 16 of 16 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 13,584 | SciTables: A Dataset and Evaluation Framework for Complex Table-to-Text Generation | 2026 | VLDB |
| 2 | 5,194 | Database Workload Characterization with Query Plan Encoders | 2022 | VLDB |
| 3 | 13,656 | Accelerating Tabular Inference: Training Data Generation with TENET | 2025 | VLDB |
| 4 | 377 | TURL: Table Understanding through Representation Learning | 2021 | VLDB |
| 5 | 11,706 | Regularized Pairwise Relationship based Analytics for Structured Data | 2023 | SIGMOD |
| 6 | 5,687 | DTT: An Example-Driven Tabular Transformer for Joinability by Leveraging Large Language Models | 2024 | SIGMOD |
| 7 | 5,840 | Pre-training Summarization Models of Structured Datasets for Cardinality Estimation | 2022 | VLDB |
| 8 | 7,254 | Incremental Tabular Learning on Heterogeneous Feature Space | 2023 | SIGMOD |
| 9 | 4,489 | ARM-Net: Adaptive Relation Modeling Network for Structured Data | 2021 | SIGMOD |
| 10 | 10,598 | AixelAsk: A Stepwise-Guided Retrieval and Reasoning Framework for Large Table QA | 2026 | SIGMOD |