Knowledge Graph Completion for Action Prediction on Situational Graphs -- A Case Study on Household Tasks
This work addresses incomplete video data analysis for household robots, but it is incremental as it highlights limitations of existing methods without introducing a new solution.
The paper tackled the problem of completing situational knowledge graphs for household action prediction, finding that many standard link prediction algorithms underperform simple baselines due to unique graph characteristics.
Knowledge Graphs are used for various purposes, including business applications, biomedical analyses, or digital twins in industry 4.0. In this paper, we investigate knowledge graphs describing household actions, which are beneficial for controlling household robots and analyzing video footage. In the latter case, the information extracted from videos is notoriously incomplete, and completing the knowledge graph for enhancing the situational picture is essential. In this paper, we show that, while a standard link prediction problem, situational knowledge graphs have special characteristics that render many link prediction algorithms not fit for the job, and unable to outperform even simple baselines.