{"678553":{"#nid":"678553","#data":{"type":"event","title":"PhD Defense |Towards Interpretable and Controllable Machine Learning Models via Logic Reasoning","body":[{"value":"\u003Cp\u003EYuan Yang - Machine Learning PhD Student - School of Computational Science and Engineering\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EDate:\u0026nbsp;\u003C\/strong\u003EDecember 2nd\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ETime:\u0026nbsp;\u003C\/strong\u003E11:00 AM \u2013 1:00 PM EST\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ELocation\u003C\/strong\u003E: Online\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EMeeting Link\u003C\/strong\u003E: \u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/94374751336\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/94374751336\u003C\/a\u003E\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003E1 Dr. Faramarz Fekri, School of Electrical and Computer Engineering, Georgia Institute of Technology (Advisor)\u003C\/p\u003E\u003Cp\u003E2 Dr. Zsolt Kira, School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E3 Dr. Larry Heck, School of Electrical and Computer Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E4 Dr. Viveck Cadambe, School of Electrical and Computer Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E5 Dr. Bo Dai, School of Computational Science and Engineering, Georgia Institute of Technology\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EModern machine learning models have provided new capabilities across a spectrum of applications in vision, reasoning, and natural language processing.\u0026nbsp; However, these models are criticized for being non-interpretable, data-inefficient, and vulnerable to subtle perturbations such as adversarial attacks and distribution shifts. Addressing these issues remains at the center of developing trustworthy ML systems for real-world applications.\u003C\/p\u003E\u003Cp\u003EOur research focuses on providing a principled solution to these issues through logic reasoning formalism.\u003C\/p\u003E\u003Cp\u003ESpecifically, we study the fundamental technique of inductive logic programming (ILP) that learns and represents patterns in knowledge graphs as first-order logic (FOL) rules, providing an interpretable approach to various reasoning tasks on structured data:\u003C\/p\u003E\u003Col\u003E\u003Cli\u003Ewe investigate the connection between model explanation and logic formalism and propose frameworks for explaining and defending ML models via logic reasoning;\u003C\/li\u003E\u003Cli\u003Ewe formalize logic reasoning methods as a novel data programming paradigm and propose data-efficient frameworks for model training and evaluation;\u003C\/li\u003E\u003Cli\u003Eto improve the expressiveness of the ILP technique, we propose to extend the model to the temporal domain and hypergraphs so that one can generalize FOL rules on complex structures\u003C\/li\u003E\u003C\/ol\u003E\u003Cp\u003EFurthermore, our research explores the integration of large language models (LLMs) with logical reasoning techniques to enhance interpretability, data efficiency, and controllability in machine learning systems. We investigate:\u003C\/p\u003E\u003Col\u003E\u003Cli\u003Ethe potential of LLMs in translating natural language to formal logical representations to solve complex reasoning problems;\u003C\/li\u003E\u003Cli\u003Eenhancing LLMs\u0027 reasoning capability on open-ended, ambiguous problems by incorporating formal logic reasoning, thereby improving their controllability and robustness beyond narrowly defined domains.\u0026nbsp;\u003C\/li\u003E\u003C\/ol\u003E\u003Cp\u003EBy combining logic reasoning with the latest advancements in LLMs, our research aims to bridge the gap between powerful ML models and the need for explainable, efficient, and reliable AI systems in real-world applications.\u003C\/p\u003E","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETowards Interpretable and Controllable Machine Learning Models via Logic Reasoning\u003C\/strong\u003E\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Yuan Yang - Machine Learning PhD Student - School of Computational Science and Engineering"}],"uid":"36518","created_gmt":"2024-11-20 13:53:49","changed_gmt":"2024-11-20 13:57:11","author":"shatcher8","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2024-12-02T11:00:00-05:00","event_time_end":"2024-12-02T13:00:00-05:00","event_time_end_last":"2024-12-02T13:00:00-05:00","gmt_time_start":"2024-12-02 16:00:00","gmt_time_end":"2024-12-02 18:00:00","gmt_time_end_last":"2024-12-02 18:00:00","rrule":null,"timezone":"America\/New_York"},"location":"https:\/\/gatech.zoom.us\/j\/94374751336","extras":[],"groups":[{"id":"576481","name":"ML@GT"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}