Dyuman Aditya

Publications

* Denotes equal contribution

1. AAAI-MAKE

   PyReason: Software for Open World Temporal Logic

   Dyuman Aditya*, Kaustuv Mukerji*, Srikar Balasubramanian, Abhiraj Chaudhary, and Paulo Shakarian

   In AAAI Spring Symposium, 2023

   Abs arXiv Bib Code Website

   The growing popularity of neuro symbolic reasoning has led to the adoption of various forms of differentiable (i.e., fuzzy) first order logic. We introduce PyReason, a software framework based on generalized annotated logic that both captures the current cohort of differentiable logics and temporal extensions to support inference over finite periods of time with capabilities for open world reasoning. Further, PyReason is implemented to directly support reasoning over graphical structures (e.g., knowledge graphs, social networks, biological networks, etc.), produces fully explainable traces of inference, and includes various practical features such as type checking and a memory-efficient implementation. This paper reviews various extensions of generalized annotated logic integrated into our implementation, our modern, efficient Python-based implementation that conducts exact yet scalable deductive inference, and a suite of experiments. PyReason is available at: github.com/lab-v2/pyreason.

   @inproceedings{aditya_pyreason_2023,
     author = {Aditya*, Dyuman and Mukerji*, Kaustuv and Balasubramanian, Srikar and Chaudhary, Abhiraj and Shakarian, Paulo},
     title = {{PyReason}: Software for Open World Temporal Logic},
     year = {2023},
     booktitle = {{AAAI} Spring Symposium},
   }

2. IEEE-ICSC

   Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning

   Kaustuv Mukerji, Devendra Parkar, Lahiri Pokala, Dyuman Aditya, and Paulo Shakarian

   In IEEE ICSC, 2023

   Abs arXiv Bib Code Website

   Recent advances in reinforcement learning (RL) have shown much promise across a variety of applications. However, issues such as scalability, explainability, and Markovian assumptions limit its applicability in certain domains. We observe that many of these shortcomings emanate from the simulator as opposed to the RL training algorithms themselves. As such, we propose a semantic proxy for simulation based on a temporal extension to annotated logic. In comparison with two high-fidelity simulators, we show up to three orders of magnitude speed-up while preserving the quality of policy learned. In addition, we show the ability to model and leverage non-Markovian dynamics and instantaneous actions while providing an explainable trace describing the outcomes of the agent actions.

   @inproceedings{mukherji2023scalable,
     author = {Mukerji, Kaustuv and Parkar, Devendra and Pokala, Lahiri and Aditya, Dyuman and Shakarian, Paulo},
     title = {Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning},
     year = {2023},
     booktitle = {{IEEE} ICSC},
   }

3. ICLP

   Geospatial Trajectory Generation via Efficient Abduction: Deployment for Independent Testing

   Divyagna Bavikadi, Dyuman Aditya, Devendra Parkar, Paulo Shakarian, Graham Mueller, Chad Parvis, and Gerardo I. Simari

   In ICLP, 2024

   Abs arXiv Bib

   The ability to generate artificial human movement patterns while meeting location and time constraints is an important problem in the security community, particularly as it enables the study of the analog problem of detecting such patterns while maintaining privacy. We frame this problem as an instance of abduction guided by a novel parsimony function represented as an aggregate truth value over an annotated logic program. This approach has the added benefit of affording explainability to an analyst user. By showing that any subset of such a program can provide a lower bound on this parsimony requirement, we are able to abduce movement trajectories efficiently through an informed (i.e., A*) search. We describe how our implementation was enhanced with the application of multiple techniques in order to be scaled and integrated with a cloud-based software stack that included bottom-up rule learning, geolocated knowledge graph retrieval/management, and interfaces with government systems for independently conducted government-run tests for which we provide results. We also report on our own experiments showing that we not only provide exact results but also scale to very large scenarios and provide realistic agent trajectories that can go undetected by machine learning anomaly detectors.

   @inproceedings{bavikadi2024geospatialtrajectorygenerationefficient,
     author = {Bavikadi, Divyagna and Aditya, Dyuman and Parkar, Devendra and Shakarian, Paulo and Mueller, Graham and Parvis, Chad and Simari, Gerardo I.},
     title = {Geospatial Trajectory Generation via Efficient Abduction: Deployment for Independent Testing},
     year = {2024},
     booktitle = {ICLP},
   }