Abinash Maharana, MS student working under the supervision of Prof. P Krishna Reddy presented a paper on An Efficient Explainable Link Forecasting Framework for Temporal Knowledge Graphs at the 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Osaka, Japan from 25 – 28 May. The other author of this paper is Rage Uday Kiran.
Research work as explained by the authors:
Link forecasting in a temporal Knowledge Graph (tKG) involves predicting a future event from a given set of past events. Most previous studies suffered from reduced performance as they disregarded acyclic rules and enforced a tight constraint that all past events must exist in a strict temporal order. This paper proposes a novel explainable rule-based link forecasting framework by introducing two new concepts, namely ‘relaxed temporal cyclic and acyclic random walks’ and ‘link-star rules’. The former concept involves generating rules by performing cyclic and acyclic random walks on a tKG by taking into account the real-world phenomenon that the order of any two events may be ignored if their occurrence time gap is within a threshold value. Link-star rules are a special class of acyclic rules generated based on the natural phenomenon that history repeats itself after a particular time. Link-star rules eliminate the problem of combinatorial rule explosion, thereby making our framework practicable. Experimental results demonstrate that our framework outperforms the state-of-the-art by a substantial margin. The evaluation measures hits@1 and mean reciprocal rank were improved by 45% and 23%, respectively.
The Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) is one of the longest established and leading international conferences in the areas of data mining and knowledge discovery. It provides an international forum for researchers and industry practitioners to share their new ideas, original research results, and practical development experiences from all KDD related areas, including data mining, data warehousing, machine learning, artificial intelligence, databases, statistics, knowledge engineering, visualisation, decision-making systems, and the emerging applications.
Conference page: http://pakdd2023.org/
May 2023