Scaling Up ILP to Large Examples: Results on Link Discovery for Counter-Terrorism
نویسندگان
چکیده
Inductive Logic Programming (ILP) has been shown to be a viable approach to many problems in multi-relational data mining (e.g. bioinformatics). Link discovery (LD) is an important task in data mining for counter-terrorism and is the focus of DARPA's program on Evidence Extraction and Link Discovery (EELD). Learning patterns for LD is a novel problem in relational data mining that is characterized by having an unprecedented number of background facts. As a result of the explosion in the amount of background knowledge, the eÆciency of existing ILP algorithms becomes a serious limitation. This paper presents a new ILP algorithm that integrates top-down and bottom-up search in order to reduce search when processing large examples. Experimental results on EELD data con rm that it signi cantly improves eÆciency over existing ILP methods.
منابع مشابه
Scaling up Inductive Logic Programming by Learning from Interpretations Scaling up Inductive Logic Programming by Learning from Interpretations
When comparing inductive logic programming (ILP) and attribute-value learning techniques, there is a trade-oo between expressive power and eeciency. Inductive logic programming techniques are typically more expressive but also less eecient. Therefore, the data sets handled by current inductive logic programming systems are small according to general standards within the data mining community. T...
متن کاملFOIL-D: Efficiently Scaling FOIL for Multi-relational Data Mining of Large Datasets
Multi-relational rule mining is important for knowledge discovery in relational databases as it allows for discovery of patterns involving multiple relational tables. Inductive logic programming (ILP) techniques have had considerable success on a variety of multi-relational rule mining tasks, however, most ILP systems do not scale to very large datasets. In this paper we present two extensions ...
متن کاملThe Broadening Remit of UK Counter-Terrorism - from Terrorism to ‘Radicalization’ to ‘Extremism’: C-T Imperative or Loss of Focus?
This article argues that the discourses of radicalization and, more lately, of extremism have served to confuse the remit of counter-terrorism. Indeed, it appears that ‘terrorism’, ‘radicalization’ and ‘extremism’ have increasingly become merged into a single discursive framework, one consequence of which has been to blur the important distinction between ‘extremism’ of thought and ‘extremism’ ...
متن کاملEfficient Privacy-Preserving Link Discovery
Link discovery is a process of identifying association(s) among different entities included in a complex network structure. These association(s) may represent any interaction among entities, for example between people or even bank accounts. The need for link discovery arises in many applications including law enforcement, counter-terrorism, social network analysis, intrusion detection, and frau...
متن کاملPreventing Terrorism by Combating Financial Resources
Terrorism is an offensive action which violates human rights and always invades to people’s rights. Given the high incidence of this type of global action and the widespread violations of human rights and peace and security, countering terrorism will be important. The existence of financial resources is an essential element of terrorism and Preemptive measures and their success in blocking fina...
متن کامل