Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Bhushan Kotnis, Kiril Gashteovski, Daniel Rubio, Ammar Shaker, Vanesa Rodriguez-Tembras, Makoto Takamoto, Mathias Niepert, Carolin Lawrence. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Representation learning for knowledge graphs (KGs) has focused on the problem of answering simple link prediction queries. In this work we address the more ambitious challenge of predicting the answers of conjunctive queries with multiple missing entities. We propose Bidirectional Query Embedding (BiQE), a method that embeds conjunctive queries with models based on bi-directional attention mechanisms. Contrary to prior work, bidirectional self-attention can capture interactions among all the elements of a query graph. We introduce two new challenging datasets for studying conjunctive query inference and conduct experiments on several benchmark datasets that demonstrate BiQE significantly outperforms state of the art baselines.

Carolin Lawrence, Bhushan Kotnis, Mathias Niepert. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Learning relations based on evidence from knowledge repositories rely on processing the available relation instances. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form of a regularization factor added to the loss function that takes into account the types (categories) of the entities that appear as arguments to relations in the knowledge base. Tested on Freebase, a frequently used benchmarking dataset for link/path predicting tasks, we note increased performance compared to the baseline model in terms of mean reciprocal rank and [email protected], N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer.

Campaigners, advertisers, and activists are increasingly turning to social recommendation mechanisms, provided by social media, for promoting their products, services, brands, and even ideas. However, many a time, such social network-based campaigns perform poorly in practice, because the intensity of recommendations drastically reduces beyond a few hops from the source. A natural strategy for maintaining the intensity is to provide incentives. In this paper, we address the problem of minimizing the cost incurred by the campaigner for incentivizing a fraction of individuals in the social network, while ensuring that the campaign message reaches a given expected fraction of individuals. We also address the dual problem of maximizing the campaign penetration for a resource constrained campaigner. To help us understand and solve the above-mentioned problems, we use percolation theory to formally state them as optimization problems. These problems are not amenable to traditional approaches because of a fixed point equation that needs to be solved numerically. However, we use results from reliability theory to establish some key properties of the fixed point, which in turn enables us to solve these problems using algorithms that are linearithmic in maximum node degree. Furthermore, we evaluate the efficacy of the analytical solutions by performing simulations on real-world networks.

Large-scale Knowledge Bases (such as NELL, Yago, Freebase, etc.) are often sparse, i.e., a large number of valid relations between existing entities are missing.Recent research have addressed this problem by augmenting the KB graph with additional edges mined from a large text corpus while keeping the set of nodes fixed, and then using the Path Ranking Algorithm (PRA) to perform KB inference over this augmented graph.In this paper, we extend this line of work by augmenting the KB graph not only with edges, but also with bridging entities, where both the edges and bridging entities are mined from a 500 million web text corpus.Through experiments on real-world datasets, we demonstrate the value of bridging entities in improving the performance and running time of PRA in the KB inference task.