ILP 2013 – The 23rd International Conference on Inductive Logic Programming
Rio de Janeiro, Brazil, August 28-30, 2013
25/04 : Abstracts of long papers due
30/04 : Long papers due
02/06 : Notification for long papers
21/06: Short/published papers due
28/06 : Notification for short/published papers
- Hendrik Blockeel -Katolieke Universiteit Leuven, Belgium
- William Cohen – Carnegie Mellon University, USA
- Jure Leskovec – Stanford University, USA
CALL FOR PAPERS
The ILP conference series, started in 1991, is the premier international forum on learning from structured relational data. Originally focused on the induction of logic programs, it has broadened its scope and attracted a lot of attention and interest in recent years. Authors are invited to submit papers presenting original results on all aspects of learning in logic, multi-relational learning and data mining, statistical relational learning, graph and tree
mining, relational reinforcement learning, and learning in other (non-propositional) logic-based knowledge representation frameworks.
Typical, but not exclusive, topics of interest for submissions include:
- Theoretical aspects: learning scenarios, data/model representation frameworks, their computational and/or statistical properties, etc.
- Algorithms: probabilistic and statistical approaches, distance and kernel-based methods, learning with (semi)structured data, supervised, unsupervised, and semi-supervised relational learning, relational reinforcement learning, inductive databases, link discovery, new propositionalization approaches, multi-instance learning, predicate invention, logical and probabilistic inference, uncertainty reasoning.
- Representations and languages for logic-based learning: including datalog, first-order logic, description logics and ontologies, higher-order logic, probabilistic logical representations, mapping between alternative representations.
- Systems: systems that implement inductive logic programming algorithms with special emphasis on issues like optimization, parallelism, efficiency and scalability.
- applications including, but not restricted to multi-relational learning from structured (e.g., labeled graphs, tree patterns) and semi-structured data (e.g., XML documents), learning from relational data in areas of science (bioinformatics, cheminformatics, medical informatics, etc.), natural language processing (computational linguistics, text and web mining etc.), engineering, games, semantic web, the arts, etc.
We solicit three kinds of papers:
- Long papers describing original mature work containing appropriate experimental evaluation and/or representing a self-contained theoretical contribution. Long papers will be reviewed by at least 3 members of the program committee. Authors will be notified prior to the conference on acceptance/rejection for the Springer LNAI post-conference proceedings. Authors of accepted papers will be assigned a standard time slot for presentation.
- Short papers describing original work in progress, brief accounts of original ideas without conclusive experimental evaluation, and other relevant work of potentially high scientific interest but not yet qualifying for the long paper category. The PC chairs will accept/ reject short papers on the grounds of relevance. Authors of accepted short papers will be assigned a reduced time slot for presentation. Each short paper will be reviewed by at least 3 members of the program committee on the basis of both the manuscript and its presentation, and the authors of selected papers will be invited to submit a long version for the Springer LNAI post-conference proceedings; in this case, the long paper will be reviewed again by the assigned PC members of the short paper and be finally accepted if satisfactorily addressing the reviewer’s requirements.
- Papers relevant to the conference topics and recently published or accepted for publication by a first-class conference such as ECML/PKDD, ICML, KDD, ICDM, AAAI, IJCAI, etc. or journal such as MLJ, DMKD, JMLR etc. The PC chairs will accept/reject such papers on the grounds of relevance and quality of the original publication venue. Authors of accepted papers will be assigned a reduced time slot for presentation. These papers will not appear in the Springer LNAI post-conference proceedings.
Submissions in category 1 or 2 must not have been published or be under review for a journal or for another conference with published proceedings. They should be submitted in the Springer LNCS format. Long (short) papers must not exceed 12 (6) pages. Papers in category 3 should be submitted in their original format and the authors should indicate the original publication venue.
A special issue of the Machine Learning journal is planned following the conference, with papers selected by the PC from all the three categories above, significantly revised and extended to meet the MLJ criteria, and re-reviewed by the PC.
Gerson Zaverucha, UFRJ, Brazil
Vítor Santos Costa, UP, Portugal
Aline Paes, UFRJ, Brazil