( events)   Timezone:  
Fri Dec 13 08:00 AM -- 06:00 PM (PST) @ West 109 + 110
KR2ML - Knowledge Representation and Reasoning Meets Machine Learning
Veronika Thost · Christian Muise · Kartik Talamadupula · Sameer Singh · Christopher Ré

Workshop Home Page

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.

Opening Remarks (Talk)
Invited Talk (William W. Cohen) (Talk)
Contributed Talk: Neural-Guided Symbolic Regression with Asymptotic Constraints (Talk)
Contributed Talk: Towards Finding Longer Proofs (Talk)
Contributed Talk: Neural Markov Logic Networks (Talk)
Poster Spotlights A (23 posters) (Talk)
Coffee Break + Poster Session (Break)
Invited Talk (Xin Luna Dong) (Talk)
Contributed Talk: Layerwise Knowledge Extraction from Deep Convolutional Networks (Talk)
Contributed Talk: Ontology-based Interpretable Machine Learning with Learnable Anchors (Talk)
Contributed Talk: Learning multi-step spatio-temporal reasoning with Selective Attention Memory Network (Talk)
Contributed Talk: MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library (Talk)
Invited Talk (Vivek Srikumar) (Talk)
Lunch Break (Break)
Invited Talk (Francesca Rossi) (Talk)
Contributed Talk: TP-N2F: Tensor Product Representation for Natural To Formal Language Generation (Talk)
Contributed Talk: TabFact: A Large-scale Dataset for Table-based Fact Verification (Talk)
Contributed Talk: LeDeepChef: Deep Reinforcement Learning Agent for Families of Text-Based Games (Talk)
Poster Spotlights B (13 posters) (Talk)
Coffee Break + Poster Session (Break)
Invited Talk (Yejin Choi) (Talk)
Invited Talk (Guy Van den Broeck) (Talk)
Discussion Panel
Closing Remarks (Talk)