Seventh International Workshop on Statistical Relational AI
The purpose of the Statistical Relational AI (StarAI) workshop is to bring together researchers and practitioners from two fields: logical (or relational) AI and probabilistic (or statistical) AI. These fields share many key features and often solve similar problems and tasks. Until recently, however, research in them has progressed independently with little or no interaction. The fields often use different terminology for the same concepts and, as a result, keeping-up and understanding the results in the other field is cumbersome, thus slowing down research. Our long term goal is to change this by achieving a synergy between logical and statistical AI. As a stepping stone towards realizing this big picture view on AI, we are organizing the Seventh International Workshop on Statistical Relational AI at the 33rd Conference on Uncertainty in Artificial Intelligence (UAI) in Sydney, on August 15th 2017.
StarAI will be a one day workshop with short paper presentations, a poster session, and two invited speakers:
Authors should submit either a full paper reporting on novel technical contributions or work in progress (AAAI style, up to 7 pages excluding references), a short position paper (AAAI style, up to 2 pages excluding references), or an already published work (verbatim, no page limit, citing original work) in PDF format via EasyChair. All submitted papers will be carefully peer-reviewed by multiple reviewers and low-quality or off-topic papers will be rejected. Accepted papers will be presented as a short talk and poster.
Abstract: General game-playing systems can understand descriptions of new games at runtime and learn to play them without human intervention. In the first part of this talk, I will give an overview of the Game Description Language (GDL) as a formal representation language for general games. I will show how to model imperfect-information games and so-called epistemic games, in which rules depend on what players can and cannot deduce from the information they get during gameplay. In the second part, I will give an overview of successful approaches to general game playing and in particular discuss methods to represent and automatically generate game-specific knowledge from a set of game rules.
Abstract: Representation learning has become an invaluable approach for making statistical inferences from relational data. In this talk, I will first give an overview over state-of-the-art methods for learning representations of multi-relational data and discuss how they can be used for tasks such as link prediction and entity resolution. However, while complex relational datasets often exhibit a latent hierarchical structure, such embeddings typically do not account for this property. In the second part of the talk, I will introduce a novel approach to learning such hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincaré ball. I will discuss how the underlying hyperbolic geometry allows us to learn parsimonious representations which simultaneously capture hierarchy and similarity. Furthermore, I will show that Poincaré embeddings can outperform Euclidean embeddings significantly on data with latent hierarchies, both in terms of representation capacity and in terms of generalization ability. (slides)
StarAI is currently provoking a lot of new research and has tremendous theoretical and practical implications. Theoretically, combining logic and probability in a unified representation and building general-purpose reasoning tools for it has been the dream of AI, dating back to the late 1980s. Practically, successful StarAI tools will enable new applications in several large, complex real-world domains including those involving big data, social networks, natural language processing, bioinformatics, the web, robotics and computer vision. Such domains are often characterized by rich relational structure and large amounts of uncertainty. Logic helps to effectively handle the former while probability helps her effectively manage the latter. We seek to invite researchers in all subfields of AI to attend the workshop and to explore together how to reach the goals imagined by the early AI pioneers.
The focus of the workshop will be on general-purpose representation, reasoning and learning tools for StarAI as well as practical applications. Specifically, the workshop will encourage active participation from researchers in the following communities: satisfiability (SAT), knowledge representation (KR), constraint satisfaction and programming (CP), (inductive) logic programming (LP and ILP), graphical models and probabilistic reasoning (UAI), statistical learning (NIPS, ICML, and AISTATS), graph mining (KDD and ECML PKDD) and probabilistic databases (VLDB and SIGMOD). It will also actively involve researchers from more applied communities, such as natural language processing (ACL and EMNLP), information retrieval (SIGIR, WWW and WSDM), vision (CVPR and ICCV), semantic web (ISWC and ESWC) and robotics (RSS and ICRA).
Previous StarAI workshops were held in conjunction with AAAI 2010, UAI 2012, AAAI 2013, AAAI 2014, UAI 2015, and IJCAI 2016 and were among the most popular workshops at the conferences.