Report on The Twelfth International Conference on Inductive Logic Programming (ILP 2002)
Sydney, Australia, July 9-11, 2002

Stan Matwin and Claude Sammut

The twelfth international conference on Inductive Logic Programming (ILP 2002) took place in Sydney, Australia, on July 9-11th, 2002. It was collocated with the Nineteenth International Conference on Machine Learning (ICML-2002), and with the Fifteenth Annual Conference on Computational Learning Theory (COLT-2002). Continuing a series of international conferences devoted to Inductive Logic Programming and Relational Learning ILP 2002 was the central event in 2002 for researchers interested in learning relational knowledge from examples.

The Programme Committee, following a resolution of the Community Meeting.in Strasbourg in September, 2001, took upon itself the issue of the possible change of the name of the conference. Following an extended email discussion, a number of proposed names was subject to a vote. In the first stage of the vote, two names were retained for the second vote. The two names were: Inductive Logic Programming and Relational Learning. It has been decided that a 60% vote would be needed to change the name; the result of the vote was 57% in favour of the name Relational Learning. Consequently, the name Inductive Logic Programming was kept.

Since the initial submission deadline resulted in too few submissions, the Programme Committee decided to extend the deadline and at the same time publish the Proceedings after the conference (the extended deadline was cutting into the time needed by the publisher to produce the proceedings from the camera-ready copy). At the extended deadline there were 43 submissions to the conference, which resulted in 21 accepted papers, of which two withdrew and nineteen were presented.

The conference programme consisted of two invited talks, the presentations of accepted technical papers, a Work in Progress session, and a panel. The invited talk by John Shawe-Taylor introduced the concept of the Set Covering Machine and its relations to ILP. The second invited talk, by Saso Dzeroski, joint with ICML, reviewed the goals of ILP and showed how they fruitfully support Computational Scientific Discovery. There was a Work in Progress session with ten papers, whose abstracts were published in a separate booklet. Furthermore, there was a Panel "If I had to start a Ph.D. in ILP today, what would my topic be?" with the following panelists: I. Bratko, P. Flach, J. Lloyd , S. Muggleton, C. Rouveirol, P. Tadepalli, and L. Saitta, chaired by S. Matwin.

The ILP 2002 technical programme, similarly to previous editions of the conference, covered a broad range of topics, from implementation techniques to applications, and from kernels for structured data to associations for relational data.

ILP 2002 would not have been possible without the generous support of ILPNet2 to European participants. This is kindly acknowledged.