Investigating the Effect of Hard Negative Sample Distribution on Contrastive Knowledge Graph Embedding

The success of the knowledge graph completion task heavily depends on the quality of the knowledge graph embeddings (KGEs), which relies on self-supervised learning and augmenting the dataset with negative triples. There is a gap in literature between the theoretical analysis of negative samples on contrastive loss and heuristic generation of quality (i.e., hard) negative triples. In this paper, we modify the InfoNCE loss to explicitly account for the negative sample distribution. We show minimizing InfoNCE loss with hard negatives maximizes the KL-divergence between the given and negative triple embedding. However, we also show that hard negatives can lead to false negatives (i.e., accidentally factual triples) and reduce downstream task performance. To address this issue, we propose a novel negative sample distribution that uses the graph structure of the knowledge graph to remove the false negative triples. We call our algorithm Hardness and Structure-aware (\textbf{HaSa}) contrastive KGE. Experiments show that our method outperforms state-of-the-art KGE methods in several metrics for WN18RR and FB15k-237 datasets.

How News Evolves? Modeling News Text and Coverage using Graphs and Hawkes Process

Monitoring news content automatically is an important problem. The news content, unlike traditional text, has a temporal component. However, few works have explored the combination of natural language processing and dynamic system models. One reason is that it is challenging to mathematically model the nuances of natural language. In this paper, we discuss how we built a novel dataset of news articles collected over time. Then, we present a method of converting news text collected over time to a sequence of directed multi-graphs, which represent semantic triples (Subject ! Predicate ! Object). We model the dynamics of specific topological changes from these graphs using discrete-time Hawkes processes. With our real-world data, we show that analyzing the structures of the graphs and the discrete-time Hawkes process model can yield insights on how the news events were covered and how to predict how it may be covered in the future.