KR2ML - Knowledge Representation and Reasoning Meets Machine Learning
Veronika Thost · Christian Muise · Kartik Talamadupula · Sameer Singh · Christopher Ré

Fri Dec 13th 08:00 AM -- 06:00 PM @ West 109 + 110
Event URL: »

Machine learning (ML) has seen a tremendous amount of recent success and has been applied in a variety of applications. However, it comes with several drawbacks, such as the need for large amounts of training data and the lack of explainability and verifiability of the results. In many domains, there is structured knowledge (e.g., from electronic health records, laws, clinical guidelines, or common sense knowledge) which can be leveraged for reasoning in an informed way (i.e., including the information encoded in the knowledge representation itself) in order to obtain high quality answers. Symbolic approaches for knowledge representation and reasoning (KRR) are less prominent today - mainly due to their lack of scalability - but their strength lies in the verifiable and interpretable reasoning that can be accomplished. The KR2ML workshop aims at the intersection of these two subfields of AI. It will shine a light on the synergies that (could/should) exist between KRR and ML, and will initiate a discussion about the key challenges in the field.

08:00 AM Opening Remarks (Talk)
08:05 AM Invited Talk (William W. Cohen) (Talk) William Cohen
08:35 AM Contributed Talk: Neural-Guided Symbolic Regression with Asymptotic Constraints (Talk) Rishabh Singh
08:50 AM Contributed Talk: Towards Finding Longer Proofs (Talk) Zsolt Zombori
09:05 AM Contributed Talk: Neural Markov Logic Networks (Talk) Ondrej Kuzelka
09:20 AM Poster Spotlights A (23 posters) (Talk)
DongHa Bahn, Xiaoran (Sean) Xu, Shih-Chieh Su, Dan Cunnington, Wonseok Hwang, Sarthak Dash, Alberto Camacho, Theodoros Salonidis, Shiyang Li, Yuyu Zhang, Habibeh Naderi, Zhe Zeng, Pasha Khosravi, Pedro Colon-Hernandez, Dimitris Diochnos, David Windridge, Robin Manhaeve, Vaishak Belle, Brendan Juba, Naveen Sundar Govindarajulu, Joe Bockhorst
09:45 AM Coffee Break + Poster Session (Break)
10:30 AM Invited Talk (Xin Luna Dong) (Talk) Luna Dong
11:00 AM Contributed Talk: Layerwise Knowledge Extraction from Deep Convolutional Networks (Talk) Simon Odense
11:15 AM Contributed Talk: Ontology-based Interpretable Machine Learning with Learnable Anchors (Talk) Thi Kim Phung Lai
11:30 AM Contributed Talk: Learning multi-step spatio-temporal reasoning with Selective Attention Memory Network (Talk) T.S. Jayram
11:45 AM Contributed Talk: MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library (Talk) Dmitry Kazhdan
12:00 PM Invited Talk (Vivek Srikumar) (Talk) Vivek Srikumar
12:30 PM Lunch Break (Break)
02:00 PM Invited Talk (Francesca Rossi) (Talk) Francesca Rossi
02:30 PM Contributed Talk: TP-N2F: Tensor Product Representation for Natural To Formal Language Generation (Talk) Kezhen Chen
02:45 PM Contributed Talk: TabFact: A Large-scale Dataset for Table-based Fact Verification (Talk) Wenhu Chen
03:00 PM Contributed Talk: LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games (Talk) Leonard Adolphs
03:15 PM Poster Spotlights B (13 posters) (Talk)
Alberto Camacho, Chris Percy, Vaishak Belle, Beliz Gunel, Toryn Klassen, Tillman Weyde, Mohamed Ghalwash, Siddhant Arora, León Illanes, Jonathan Raiman, Qing Wang, Alexander Lew, Tiffany Min
03:30 PM Coffee Break + Poster Session (Break)
04:15 PM Invited Talk (Yejin Choi) (Talk) Yejin Choi
04:45 PM Invited Talk (Guy Van den Broeck) (Talk) Guy Van den Broeck
05:15 PM Discussion Panel <span> <a href="#"></a> </span>
05:55 PM Closing Remarks (Talk)

Author Information

Veronika Thost (MIT-IBM Watson AI Lab)
Christian Muise (IBM Research AI)
Kartik Talamadupula (IBM Research)
Sameer Singh (University of California, Irvine)
Chris Ré (Stanford)

More from the Same Authors