Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks
Summary: Pool of Experts (PoE) enables train-free construction of models by extracting and composing expert modules from a pretrained network via distillation. Train-free consolidation fuses needed experts for a query, yielding compact, accurate models far faster than training. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Hakbin Kim (Inha University)
- 2. Dong-Wan Choi (Inha University)
BibTeX Citation
@inproceedings{kim_sigmod21,
title = {{Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural Networks}},
author = {Kim, Hakbin and Choi, Dong-Wan},
series = {{SIGMOD} '21},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3448016.3457326},
url = {https://dl.acm.org/doi/10.1145/3448016.3457326},
year = {2021}
}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 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 569 | BlazeIt: Optimizing Declarative Aggregation and Limit Queries for Neural Network-Based Video Analytics | 2020 | VLDB | 0.00016348191 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 8,979 | Cerebro: A Layered Data Platform for Scalable Deep Learning | 2021 | CIDR |
| 2 | 9,215 | Deep Query Optimization | 2019 | SIGMOD |
| 3 | 5,712 | Sample-Efficient Cardinality Estimation Using Geometric Deep Learning | 2024 | VLDB |
| 4 | 563 | Plan-Structured Deep Neural Network Models for Query Performance Prediction | 2019 | VLDB |
| 5 | 13,375 | Reimagining Deep Learning Systems Through the Lens of Data Systems | 2024 | VLDB |
| 6 | 6,960 | DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation | 2022 | VLDB |
| 7 | 6,038 | Efficient Construction of Approximate Ad-Hoc ML models Through Materialization and Reuse | 2018 | VLDB |
| 8 | 9,353 | On Efficient Approximate Queries over Machine Learning Models | 2023 | VLDB |
| 9 | 323 | DeepDB: Learn from Data, not from Queries! | 2020 | VLDB |
| 10 | 8,883 | FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement | 2023 | SIGMOD |