arXiv research

GG-SAGE predicts links in directed graphs with attributes, outperforming existing methods.

Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods. In particular, graph AE and VAE were successfully leveraged to tackle the challenging link prediction problem, aiming at figuring out whether some pairs of nodes from a graph are connected by unobserved edges…

New methods improve neural directed link prediction across all sub-tasks.

TSAM predicts directed temporal links using GCN and self-attention.

SELO model predicts link signs better than SDGNN using subgraph encoding and linear optimization.

Proposes a novel approach using vector cross product to preserve directional edges in directed graphs.

A new method learns node embeddings for signed directed networks by capturing both first-order and high-order topologies.

The paper presents a new method to represent directed graphs using pseudo-Riemannian manifolds.

A new algorithm learns graph embeddings considering directionality, improving multiple tasks.

Novel GNN for signed and directed networks using magnetic signed Laplacian.

We propose a novel approach for learning node representations in directed graphs, which maintains separate views or embedding spaces for the two distinct node roles induced by the directionality of the edges. We argue that the previous approaches either fail to encode the edge directionality or their encodings cannot b…

Geometrically describes the linear and quadratic forms for rational links.

We propose a link prediction algorithm that is based on spring-electrical models. The idea to study these models came from the fact that spring-electrical models have been successfully used for networks visualization. A good network visualization usually implies that nodes similar in terms of network topology, e.g., co…

Unified framework linking firm signals and cross-asset spillovers for SDF estimation.

Relational data are usually highly incomplete in practice, which inspires us to leverage side information to improve the performance of community detection and link prediction. This paper presents a Bayesian probabilistic approach that incorporates various kinds of node attributes encoded in binary form in relational m…

The ubiquitous proliferation of online social networks has led to the widescale emergence of relational graphs expressing unique patterns in link formation and descriptive user node features. Matrix Factorization and Completion have become popular methods for Link Prediction due to the low rank nature of mutual node fr…

We consider intrinsic linking and knotting in the context of directed graphs. We construct an example of a directed graph that contains a consistently oriented knotted cycle in every embedding. We also construct examples of intrinsically 3-linked and 4-linked directed graphs. We introduce two operations, consistent edg…

RVFL NNs perform well without direct links and output bias for regression.

It has often been taken as a working assumption that directed links in information networks are frequently formed by "short-cutting" a two-step path between the source and the destination -- a kind of implicit "link copying" analogous to the process of triadic closure in social networks. Despite the role of this assump…

Equity-Directed Bootstrapping improves model performance across groups in imbalanced datasets.

Authors create déjà vu links in Legendrian geometry.

A directed graph $G$ is $\textit{intrinsically linked}$ if every embedding of that graph contains a non-split link $L$, where each component of $L$ is a consistently oriented cycle in $G$. A $\textit{tournament}$ is a directed graph where each pair of vertices is connected by exactly one directed edge. We consider intr…

New method for efficient ERG fitting on large graphs.

During the last two decades, we easilly see that the World Wide Web's link structure is modeled as the directed graph. In this paper, we will model the World Wide Web's link structure as the directed hypergraph. Moreover, we will develop the PageRank algorithm for this directed hypergraph. Due to the lack of the World …

Fleming and Foisy recently proved the existence of a digraph whose every embedding contains a $4$-component link, and left open the possibility that a directed graph with an intrinsic $n$-component link might exist. We show that, indeed, this is the case. In fact, much as Flapan, Mellor, and Naimi show for graphs, knot…

BScNets expands graph learning to higher-order interactions.

Study news networks to predict stock returns.

Proposes a novel tensor-based approach for multi-level link prediction.

Paper constructs motifs from planar tilings for DP weaves and polycatenanes.

Neural-symbolic model improves link prediction in knowledge graphs.

ALPINE predicts links in networks by querying the most informative pairs.

DEAL model predicts links for new nodes with only attribute info.

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

FakeEdge tackles dataset shift in link prediction tasks.

Develops a new causal model for path-dependent link prediction.

NPGNN improves graph link prediction by adapting to new graphs.

Classifies intrinsically linked tournaments by their score sequences.

Link prediction is an important way to complete knowledge graphs (KGs), while embedding-based methods, effective for link prediction in KGs, perform poorly on relations that only have a few associative triples. In this work, we propose a Meta Relational Learning (MetaR) framework to do the common but challenging few-sh…

Recent developments have linked causal inference with Algorithmic Information Theory, and methods have been developed that utilize Conditional Kolmogorov Complexity to determine causation between two random variables. We present a method for inferring causal direction between continuous variables by using an MDL Binnin…

In the present paper, we construct the Khovanov homology theory for virtual links. Besides the direct approach with Z_{2} coefficients we also describe the Khovanov homology for framed links and the Khovanov homology using ``double cover''. The latter two approaches are based on the notion of ``atom''.

Paper introduces models to discover complex structures in large hypergraphs.

Let $D$ be an oriented classical or virtual link diagram with directed universe $\vec{U}$. Let $C$ denote a set of directed Euler circuits, one in each connected component of $U$. There is then an associated looped interlacement graph $L(D,C)$ whose construction involves very little geometric information about the way …

The data in many disciplines such as social networks, web analysis, etc. is link-based, and the link structure can be exploited for many different data mining tasks. In this paper, we consider the problem of temporal link prediction: Given link data for times 1 through T, can we predict the links at time T+1? If our da…

The paper classifies links up to link-homotopy using claspers.

Stochastic blockmodels (SBM) and their variants, $e.g.$, mixed-membership and overlapping stochastic blockmodels, are latent variable based generative models for graphs. They have proven to be successful for various tasks, such as discovering the community structure and link prediction on graph-structured data. Recentl…

Link prediction in a graph is the problem of detecting the missing links that would be formed in the near future. Using a graph representation of the data, we can convert the problem of classification to the problem of link prediction which aims at finding the missing links between the unlabeled data (unlabeled nodes) …

New framework tackles fairness in link prediction beyond demographic parity.

New heuristics for predicting links in multiplex networks.