The increasing scale of encyclopedic knowledge graphs (KGs) calls for summarization as a way to help users efficiently access and distill world knowledge. Motivated by the disparity between individuals' limited information needs and the massive scale of KGs, in this paper we propose a new problem called personalized knowledge graph summarization. The goal is to construct compact "personal summaries" of KGs containing only the facts most relevant to individuals' interests. Such summaries can be stored and utilized on-device, allowing individuals private, anytime access to the information that interests them most.We formalize the problem as one of constructing a sparse graph, or summary, that maximizes a user's inferred "utility" over a given KG, subject to a user-and device-specific constraint on the summary's size. To solve it, we propose GLIMPSE, a summarization framework that provides theoretical guarantees on the summary's utility and is linear in the number of edges in the KG. In an evaluation with real user queries to opensource, encyclopedic KGs of up to one billion triples, we show that GLIMPSE efficiently creates summaries that outperform strong baselines by up to 19% in query answering F1 score.
We study the evaluation of graph explanation methods. The state of the art to evaluate explanation methods is to first train a GNN, then generate explanations, and finally compare those explanations with the ground truth. We show five pitfalls that sabotage this pipeline because the GNN does not use the ground-truth edges. Thus, the explanation method cannot detect the ground truth. We propose three novel benchmarks: (i) pattern detection, (ii) community detection, and (iii) handling negative evidence and gradient saturation. In a re-evaluation of state-of-the-art explanation methods, we show paths for improving existing methods and highlight further paths for GNN explanation research.
CCS CONCEPTS• Computing methodologies → Neural networks.
Graph Neural Networks (GNNs) are the first choice for learning algorithms on graph data. GNNs promise to integrate (i) node features as well as (ii) edge information in an end-to-end learning algorithm. How does this promise work out practically? In this paper, we study to what extend GNNs are necessary to solve prominent graph classification problems. We find that for graph classification, a GNN is not more than the sum of its parts. We also find that, unlike features, predictions with an edge-only model do not always transfer to GNNs.
This report examines the derivation of a general order, multiple input version of the fast transversal recursive least squares filter algorithm. The new algorithm, in which the order (or number of taps) associated with each input channel is independent, is distinguished from the previously published multichannel form of fast transversal RLS algorithm, wherein each input channel is constrained to have the same order. This additional flexibility allows assignment of filter resources to particular channels, or independent assignment to the pole/ zero estimators in an ARMA system identification application. A summary of the new algorithm is given, in proper order of execution. An operations count is also provided for each equation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.