Distributed Online Learning of Event Definitions
This work addresses the need for efficient event recognition in streaming data, though it is incremental as it builds on an existing ILP system.
The paper tackled the problem of learning event definitions from data streams by extending the OLED system to support distributed, online learning, resulting in significantly reduced training times with minimal communication between nodes.
Logic-based event recognition systems infer occurrences of events in time using a set of event definitions in the form of first-order rules. The Event Calculus is a temporal logic that has been used as a basis in event recognition applications, providing among others, direct connections to machine learning, via Inductive Logic Programming (ILP). OLED is a recently proposed ILP system that learns event definitions in the form of Event Calculus theories, in a single pass over a data stream. In this work we present a version of OLED that allows for distributed, online learning. We evaluate our approach on a benchmark activity recognition dataset and show that we can significantly reduce training times, exchanging minimal information between processing nodes.