Fact Checking via Path Embedding and Aggregation

Knowledge graphs (KGs) are a useful source of background knowledge to (dis)prove facts of the form (s, p, o). Finding paths between s and o is the cornerstone of several fact-checking approaches. While paths are useful to (visually) explain why a given fact is true or false, it is not completely clear how to identify paths that are most relevant to a fact, encode them and weigh their importance. The goal of this paper is to present the Fact Checking via path Embedding and Aggregation (FEA) system. FEA starts by carefully collecting the paths between s and o that are most semantically related to the domain of p. However, instead of directly working with this subset of all paths, it learns vectorized path representations, aggregates them according to different strategies, and use them to finally (dis)prove a fact. We conducted a large set of experiments on a variety of KGs and found that our hybrid solution brings some benefits in terms of performance.

Toward Edge-Centric Network Embeddings

Existing network embedding approaches tackle the problem of learning low-dimensional node representations. However, networks can also be seen in the light of edges interlinking pairs of nodes. The broad goal of this paper is to introduce edge-centric network embeddings. We present an approach called ECNE, which instead of computing node embeddings directly, computes edge embeddings by relying on the notion of line graph coupled with an edge weighting mechanism to preserve the dynamic of the original graph in the line graph. We also present a link prediction framework called ECNE-LP, which given a target link (u,v) first collects paths between nodes u and v, then directly embeds the edges in these paths, and finally aggregates them toward predicting the existence of a link. We show that both ECNE and ECNE-LP bring benefit wrt the state-of-the-art.

From Community Detection to Community Deception

The community deception problem is about how to hide a target community C from community detection algorithms. The need for deception emerges whenever a group of entities (e.g., activists, police enforcements) want to cooperate while concealing their existence as a community. In this paper we introduce and formalize the community deception problem. To solve this problem, we describe algorithms that carefully rewire the connections of C's members. We experimentally show how several existing community detection algorithms can be deceived, and quantify the level of deception by introducing a deception score. We believe that our study is intriguing since, while showing how deception can be realized it raises awareness for the design of novel detection algorithms robust to deception techniques.