INFORMS Open Forum

The Hawaii International Conference on System Sciences (HICSS) invites submission of: Short Papers- Interpretable Machine Learning Minitrack

  • 1.  The Hawaii International Conference on System Sciences (HICSS) invites submission of: Short Papers- Interpretable Machine Learning Minitrack

    Posted 05-14-2022 08:56

    Machine learning (ML) has garnered significant interest in recent years due to its applicability to a wide range of complicated problems. There is increasing realization that ML models, in addition to making predictions, reveal information about relationships between domain data items, commonly referred to as interpretability of the model. A similar situation is occurring in the artificial intelligence (AI) scientific community, which has concentrated on explainable AI (XAI) along the dimensions of algorithmic interpretability, explainability, transparency, and accountability of algorithmic judgments. ML approaches may be classified as white-box or black-box; while white-box techniques like rule learners and inductive logic programming provide explicit models that are intrinsically interpretable, black-box techniques, such as (deep) neural networks, provide opaque models. With the growing use of ML, there have been significant social concerns about implementing black-box models for decisions requiring the explanation of domain relationships. The ability to express information obtained from ML models in human-comprehensible language -aka interpretability- has sparked considerable attention in academics and industry. These interpretations have found applications in healthcare, transportation, finance, education, policymaking, criminal justice, etc. As it evolves, one aim in ML is the development of interpretable techniques and models that explain themselves and their output.

    This minitrack invites papers on advancements in interpretable ML from the modeling and learning perspectives. We are looking for high-quality, original articles presenting work on the following (not exhaustive) topics:

    • Probabilistic graphical model applications
    • Rule learning for interpretable machine learning
    • Interpretation of black-box models
    • Interpretability in reinforcement learning
    • Interpretable supervised and unsupervised models
    • Interpretation of neural networks and ensemble-based methods
    • Interpretations of random forests and other ensemble models
    • Causality of machine learning models
    • Novel applications requiring interpretability
    • Methodologies for measuring interpretability of machine learning models
    • Interpretability-accuracy trade-off and its benchmarks

    Important Dates for Paper Submission

    • April 15: Paper Submission System Reopened for HICSS-56
    • June 15: Paper Submission Deadline
    • August 17: Notification of Acceptance/Rejection
    • September 4: Deadline for authors whose papers are conditionally accepted to submit a revised manuscript
    • September 22: Deadline for Authors to Submit Final Manuscript for Publication
    • October 1: Deadline for at least one author of each paper to register for the conference

    Important Dates for Pre-Conference Doctoral Consortium Application

    • September 6: Application Deadline
    • September 29: Notification of Acceptance/Rejection

    Minitrack Co-Chairs:

    Kazim Topuz (Primary Contact)
    University of Tulsa
    kazim-topuz@utulsa.edu

    Akhilesh Bajaj
    University of Tulsa
    akhilesh-bajaj@utulsa.edu

    Ismail Abdulrashid
    University of Tulsa
    ismail-abdulrashid@utulsa.edu



    ------------------------------
    Kazim Topuz
    Assistant Professor of Business Analytics
    University of Tulsa
    Tulsa OK
    ------------------------------