Embedding Learning with Events in Heterogeneous Information Networks

Abstract

In real-world applications, objects of multiple types are interconnected, forming <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Heterogeneous Information Networks</i> . In such heterogeneous information networks, we make the key observation that many interactions happen due to some <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">event</i> and the objects in each event form a complete semantic unit. By taking advantage of such a property, we propose a generic framework called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>H</b>yper<b>E</b>dge- </i> <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</b> <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ased</i> <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</b> <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mbedding</i> ( <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hebe</small> ) to learn object embeddings with events in heterogeneous information networks, where a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">hyperedge</i> encompasses the objects participating in one event. The <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hebe</small> framework models the proximity among objects in each event with two methods: (1) predicting a target object given other participating objects in the event, and (2) predicting if the event can be observed given all the participating objects. Since each hyperedge encapsulates more information of a given event, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hebe</small> is robust to data sparseness and noise. In addition, <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hebe</small> is scalable when the data size spirals. Extensive experiments on large-scale real-world datasets show the efficacy and robustness of the proposed framework.