TorchQL: A Programming Framework for Integrity Constraints in Machine Learning
Finding errors in machine learning applications requires a thorough exploration of their behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the abstractions needed to scale this process. We present TorchQL, a programming framework to evaluate and improve the correctness of machine learning applications. TorchQL allows users to write queries to specify and check integrity constraints over machine learning models and datasets. It seamlessly integrates relational algebra with functional programming to allow for highly expressive queries using only eight intuitive operators. We evaluate TorchQL on diverse use-cases including finding critical temporal inconsistencies in objects detected across video frames in autonomous driving, finding data imputation errors in time-series medical records, finding data labeling errors in real-world images, and evaluating biases and constraining outputs of language models. Our experiments show that TorchQL enables up to 13x faster query executions than baselines like Pandas and MongoDB, and up to 40% shorter queries than native Python. We also conduct a user study and find that TorchQL is natural enough for developers familiar with Python to specify complex integrity constraints.
Wed 23 OctDisplayed time zone: Pacific Time (US & Canada) change
16:00 - 17:40 | Performance Analysis and Optimisation 2OOPSLA 2024 at IBR West Chair(s): Matthew Flatt University of Utah | ||
16:00 20mTalk | Jmvx: Fast Multi-threaded Multi-Version eXecution and Record-Replay for Managed Languages OOPSLA 2024 David Schwartz University of Illinois at Chicago, Ankith Kowshik University of Illinois Chicago, Luís Pina University of Illinois at Chicago DOI | ||
16:20 20mTalk | libLISA: Instruction Discovery and Analysis on x86-64 OOPSLA 2024 Jos Craaijo Open Universiteit, Freek Verbeek Open Universiteit & Virginia Tech, Binoy Ravindran Virginia Tech DOI | ||
16:40 20mTalk | Extending the C/C++ Memory Model with Inline Assembly OOPSLA 2024 Paulo Emílio de Vilhena Imperial College London, Ori Lahav Tel Aviv University, Viktor Vafeiadis MPI-SWS, Azalea Raad Imperial College London DOI | ||
17:00 20mTalk | TorchQL: A Programming Framework for Integrity Constraints in Machine Learning OOPSLA 2024 Aaditya Naik University of Pennsylvania, Adam Stein University of Pennsylvania, Yinjun Wu University of Pennsylvania, Mayur Naik University of Pennsylvania, Eric Wong DOI | ||
17:20 20mTalk | Verification of Neural Networks' Global RobustnessRemote OOPSLA 2024 DOI |