WindTunnel: Towards Differentiable ML Pipelines Beyond a Single Model
Summary: WindTunnel converts ML pipelines (DAGs of transforms and models) into a differentiable neural-module pipeline and jointly optimizes via backprop. It translates non-diff operators (GBMs, categorical encoders) for end-to-end fine-tuning, boosting final accuracy. (summarized by gpt-5-nano on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Gyeong-In Yu
- 2. Saeed Amizadeh
- 3. Sehoon Kim
- 4. Artidoro Pagnoni
- 5. Ce Zhang
- 6. Byung-Gon Chun
- 7. Markus Weimer
- 8. Matteo Interlandi
Incoming Citations (Sorted by Pagerank)
Showing 4 of 4 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,327 | The Tensor Data Platform: Towards an AI-centric Database System | 2023 | CIDR | 5.1083405e-05 |
| 8,743 | CtxPipe: Context-aware Data Preparation Pipeline Construction for Machine Learning | 2024 | SIGMOD | 4.456315e-05 |
| 9,806 | The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format | 2024 | SIGMOD | 4.2805224e-05 |
| 11,041 | QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models | 2024 | VLDB | 4.1945683e-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 |
|---|---|---|---|---|
| 850 | Scaling Factorization Machines to Relational Data | 2013 | VLDB | 0.00015955971 |
| 4,701 | Tensors: An abstraction for general data processing | 2021 | VLDB | 5.9866564e-05 |
Previous
Page 1 / 1
Next