Title
PYLON: A PyTorch Framework for Learning with Constraints.
Abstract
Deep learning excels at learning task information from large amounts of data, but struggles with learning from declarative high-level knowledge that can be more succinctly expressed directly. In this work, we introduce PYLON, a neuro-symbolic training framework that builds on PyTorch to augment procedurally trained models with declaratively specified knowledge. PYLON lets users programmatically specify constraints as Python functions and compiles them into a differentiable loss, thus training predictive models that fit the data whilst satisfying the specified constraints. PYLON includes both exact as well as approximate compilers to efficiently compute the loss, employing fuzzy logic, sampling methods, and circuits, ensuring scalability even to complex models and constraints. Crucially, a guiding principle in designing PYLON is the ease with which any existing deep learning codebase can be extended to learn from constraints in a few lines code: a function that expresses the constraint, and a single line to compile it into a loss. Our demo comprises of models in NLP, computer vision, logical games, and knowledge graphs that can be interactively trained using constraints as supervision.
Year
Venue
Keywords
2022
AAAI Conference on Artificial Intelligence
Neuro-symbolic Reasoning,Constraints,Structured Prediction,Probabilistic Reasoning,Logic
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
9
Name
Order
Citations
PageRank
Ahmed Kareem Syed110.77
Tao Li2116.27
Thy Ton300.34
Quan Guo400.68
Kai-Wei Chang54735276.81
Parisa Kordjamshidi614318.52
Vivek Srikumar751138.58
Guy Van den Broeck800.34
Sameer Singh9106071.63