arXiv research

Wiki-CS dataset benchmarks Graph Neural Networks using Wikipedia articles.

Wikipedia is a huge opportunity for machine learning, being the largest semi-structured base of knowledge available. Because of this, many works examine its contents, and focus on structuring it in order to make it usable in learning tasks, for example by classifying it into an ontology. Beyond its textual contents, Wi…

Semantic TrueLearn uses semantic graphs to improve educational recommendation systems.

We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary size, both in the millions. We tackle these problems using a novel distributed infer…

We consider the problem of path inference: given a path prefix, i.e., a partially observed sequence of nodes in a graph, we want to predict which nodes are in the missing suffix. In particular, we focus on natural paths occurring as a by-product of the interaction of an agent with a network---a driver on the transporta…

Graph edges, along with their labels, can represent information of fundamental importance, such as links between web pages, friendship between users, the rating given by users to other users or items, and much more. We introduce LEAP, a trainable, general framework for predicting the presence and properties of edges on…

We investigate ways in which to improve the interpretability of LDA topic models by better analyzing and visualizing their outputs. We focus on examining what we refer to as topic similarity networks: graphs in which nodes represent latent topics in text collections and links represent similarity among topics. We descr…

In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate latent positions for random dot product graphs provided the latent positions are i.i.d. from some distribution. If class labels are observed for a number of vertices tending to infinity, then we show that the …

Entity linking is the task of mapping potentially ambiguous terms in text to their constituent entities in a knowledge base like Wikipedia. This is useful for organizing content, extracting structured data from textual documents, and in machine learning relevance applications like semantic search, knowledge graph const…

We present a new, efficient method for automatically detecting severe conflicts `edit wars' in Wikipedia and evaluate this method on six different language WPs. We discuss how the number of edits, reverts, the length of discussions, the burstiness of edits and reverts deviate in such pages from those following the gene…

The production and consumption of information about Bitcoin and other digital-, or 'crypto'-, currencies have grown together with their market capitalisation. However, a systematic investigation of the relationship between online attention and market dynamics, across multiple digital currencies, is still lacking. Here,…

Study proposes learning optimal priors from data for better Bayesian inference.

Singular Value Decomposition (SVD) has been used successfully in recent years in the area of recommender systems. In this paper we present how this model can be extended to consider both user ratings and information from Wikipedia. By mapping items to Wikipedia pages and quantifying their similarity, we are able to use…

We present a method to estimate block membership of nodes in a random graph generated by a stochastic blockmodel. We use an embedding procedure motivated by the random dot product graph model, a particular example of the latent position model. The embedding associates each node with a vector; these vectors are clustere…

Many prediction problems can be phrased as inferences over local neighborhoods of graphs. The graph represents the interaction between entities, and the neighborhood of each entity contains information that allows the inferences or predictions. We present an approach for applying machine learning directly to such graph…

GENRE retrieves entities autoregressively, improving efficiency and accuracy.

Learning from multiple-relational data which contains noise, ambiguities, or duplicate entities is essential to a wide range of applications such as statistical inference based on Web Linked Data, recommender systems, computational biology, and natural language processing. These tasks usually require working with very …

Inference for the stochastic blockmodel is currently of burgeoning interest in the statistical community, as well as in various application domains as diverse as social networks, citation networks, brain connectivity networks (connectomics), etc. Recent theoretical developments have shown that spectral embedding of gra…

In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings. We use an external knowledge base that is organized as a taxonomy of human-understandable concepts over entities as a guide…

As entity type systems become richer and more fine-grained, we expect the number of types assigned to a given entity to increase. However, most fine-grained typing work has focused on datasets that exhibit a low degree of type multiplicity. In this paper, we consider the high-multiplicity regime inherent in data source…

The importance of nodes in a network constantly fluctuates based on changes in the network structure as well as changes in external interest. We propose an evolving teleportation adaptation of the PageRank method to capture how changes in external interest influence the importance of a node. This framework seamlessly g…

In this work, we formalize the problem of causal inference over graph-based relational time-series data where each node in the graph has one or more time-series associated to it. We propose causal inference models for this problem that leverage both the graph topology and time-series to accurately estimate local causal…

Grammatical Error Correction (GEC) has been recently modeled using the sequence-to-sequence framework. However, unlike sequence transduction problems such as machine translation, GEC suffers from the lack of plentiful parallel data. We describe two approaches for generating large parallel datasets for GEC using publicl…

There is a well-known way to describe a link diagram as a (signed) plane graph, called its Tait graph. This concept was recently extended, providing a way to associate a set of embedded graphs (or ribbon graphs) to a link diagram. While every plane graph arises as a Tait graph of a unique link diagram, not every embedd…

TailedTS dataset benchmarks heavy-tailed time series forecasting and periodicity quantification.

The Wikimedia Foundation has recently observed that newly joining editors on Wikipedia are increasingly failing to integrate into the Wikipedia editors' community, i.e. the community is becoming increasingly harder to penetrate. To sustain healthy growth of the community, the Wikimedia Foundation aims to quantitatively…

The present paper is an introduction to a combinatorial theory arising as a natural generalisation of classical and virtual knot theory. There is a way to encode links by a class of `realisable' graphs. When passing to generic graphs with the same equivalence relations we get `graph-links'. On one hand graph-links gene…

Survey of intrinsically linked or knotted graphs.

Classifies colored links and spatial graphs up to colored link-homotopy.

The present paper is a review of the current state of Graph-Link Theory (graph-links are also closely related to homotopy classes of looped interlacement graphs), dealing with a generalisation of knots obtained by translating the Reidemeister moves for links into the language of intersection graphs of chord diagrams. I…

In many machine learning applications, one needs to interactively select a sequence of items (e.g., recommending movies based on a user's feedback) or make sequential decisions in a certain order (e.g., guiding an agent through a series of states). Not only do sequences already pose a dauntingly large search space, but…

The paper generalizes linking number properties for complete graphs.

We analyze the influence and interactions of 60 largest world banks for 195 world countries using the reduced Google matrix algorithm for the English Wikipedia network with 5 416 537 articles. While the top asset rank positions are taken by the banks of China, with China Industrial and Commercial Bank of China at the f…

NPGNN improves graph link prediction by adapting to new graphs.

New equivalence relation on ribbon graphs connects to virtual links.

GEN tackles few-shot out-of-graph link prediction in evolving multi-relational graphs.

Characterizes weakly linked pairs of complete graphs in 3D space.

We examine graphs that contain a non-trivial link in every embedding into real projective space, using a weaker notion of unlink than was used by Flapan, et al. We call such graphs intrinsically linked in projective space. We fully characterize such graphs with connectivity 0,1 and 2. We also show that only one Peterse…

Recently, Dasbach, Futer, Kalfagianni, Lin, and Stoltzfus extended the notion of a Tait graph by associating a set of ribbon graphs (or equivalently, embedded graphs) to a link diagram. Here we focus on Seifert graphs, which are the ribbon graphs of a knot or link diagram that arise from Seifert states. We provide a ch…

We study intrinsically linked graphs where we require that every embedding of the graph contains not just a non-split link, but a link that satisfies some additional property. Examples of properties we address in this paper are: a two component link with lk(A,L) = k2^r, k not 0, a non-split n-component link where all l…

We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transformer sequence-to-sequence model on 4B tokens of Wikipedia revisions and employ an iterative decoding strategy that is tailored to the loosely-…

Every link diagram can be represented as a signed ribbon graph. However, different link diagrams can be represented by the same ribbon graphs. We determine how checkerboard colourable diagrams of links in real projective space, and virtual link diagrams, that are represented by the same ribbon graphs are related to eac…

The paper explores linked cycles in graphs and their properties.

Study links and quivers, proving polynomial equality conjecture.

Paper generalizes pretzel links using spatial graphs.

We say that a graph is intrinsically non-trivial if every spatial embedding of the graph contains a non-trivial spatial subgraph. We prove that an intrinsically non-trivial graph is intrinsically linked, namely every spatial embedding of the graph contains a non-splittable 2-component link. We also show that there exis…

It is well known that surface-links in 4-space can be presented by diagrams on the plane of 4-valent spatial graphs with makers on the vertices, called marked graph diagrams. In this paper we extend the method of presenting surface-links by marked graph diagrams to presenting immersed surface-links. We also give some m…

We define an equivalence relation on graphs with signed edges, such that the associated adjacency matrices of two equivalent graphs are congruent over $\mathbb{Z}$. We show that signed graphs whose eigenvalues are larger than $-2$ are equivalent to one of the simply laced Dynkin diagrams: $A_{n}$, $D_{n}$, $E_{6}$, $E_…