Paper proposes adversarial modifications for link prediction models to improve robustness and interpretability.
problem Improving accuracy is not enough; robustness and interpretability are also crucial for link prediction models.
method Adversarial modifications to identify influential facts and evaluate model sensitivity and interpretability.
result The approach identifies the most influential facts and evaluates the sensitivity of link prediction models to additional facts.
This paper unifies observability notions for colored graphs and identifies graph modifications to improve observability.
problem Observability of colored graphs and its relationship to graph properties.
method Unified framework of observability notions, graph modifications, and NP-completeness results.
result Identification of graph modifications to improve observability and NP-completeness of one modification problem.
GOAT improves graph matching speed and accuracy using optimal transport.
problem Efficiently matching large graphs in various applications.
method Replaces linear assignment with optimal transport methods.
result GOAT provides improvements in speed and accuracy.
Novel method HAO mitigates Graph Injection Attack by preserving homophily.
problem Graph Injection Attack's high flexibility can harm graph homophily.
method Introduce homophily unnoticeability constraint and Harmonious Adversarial Objective (HAO).
result GIA with HAO breaks homophily-based defenses and outperforms previous attacks.
Lower bound on minimum vertex degree for non-negative Lin-Lu-Yau curvature on graphs.
problem Determining the minimum vertex degree for non-negative Lin-Lu-Yau curvature.
method Investigation of Ollivier-Ricci curvature and Lin-Lu-Yau modification on locally finite graphs.
result Lower bound on minimum vertex degree ensuring non-negative Lin-Lu-Yau curvature.
Many invariants of knots rely upon smoothing the knot at its crossings. To compute them, it is necessary to know how to count the number of connected components the knot diagram is broken into after the smoothing. In this paper, it is shown how to use a modification of a theorem of Zulli together with a modification of…
Researchers prove any graph can be realized as Reeb graph, linking it to manifold properties.
problem Realizing graphs as Reeb graphs on manifolds.
method Proving graphs can be realized as Reeb graphs under natural conditions, linking Reeb number to fundamental group corank.
result Reeb number equals corank of fundamental group, extending previous results.
HDT improves MCMC on graphs with history-dependent sampling.
problem Efficient sampling from target distributions on general graphs with low computational overhead.
method History-driven target (HDT) framework that replaces the original target distribution with a history-dependent one.
result Near-zero variance performance and scalability to large graphs with memory-efficient implementation.
New model improves graph attention for relational data.
problem Improving graph attention models for relational data.
method Relational Graph Attention Networks (R-GAT) extending non-relational graph attention to relational data.
result R-GAT performs worse than expected, but some configurations marginally improve molecular property modeling.
Can one reduce the size of a graph without significantly altering its basic properties? The graph reduction problem is hereby approached from the perspective of restricted spectral approximation, a modification of the spectral similarity measure used for graph sparsification. This choice is motivated by the observation…
Drawing together techniques from combinatorics and computer science, we improve the census algorithm for enumerating closed minimal P^2-irreducible 3-manifold triangulations. In particular, new constraints are proven for face pairing graphs, and pruning techniques are improved using a modification of the union-find alg…
We present a graph-based variational algorithm for multiclass classification of high-dimensional data, motivated by total variation techniques. The energy functional is based on a diffuse interface model with a periodic potential. We augment the model by introducing an alternative measure of smoothness that preserves s…
The paper extends foam theory to more complex trivalent graphs.
problem Extending foam theory to more complex trivalent graphs.
method Considering foams with singular vertices homeomorphic to cones over more general planar trivalent graphs.
result Modules associated with the dodecahedron graph are free of rank 60.
New knot invariant from 3-braids and 6-valent graphs.
problem Classical knot invariant construction.
method Using group Gn3 and plat closure of braids, define a map to framed 6-valent graphs. result Obtained a knot invariant valued in equivalence classes of graphs.
This paper presents VEC-NBT, a variation on the unsupervised graph clustering technique VEC, which improves upon the performance of the original algorithm significantly for sparse graphs. VEC employs a novel application of the state-of-the-art word2vec model to embed a graph in Euclidean space via random walks on the n…
In this paper, we study classes of graphs with three types of edges that capture the modified independence structure of a directed acyclic graph (DAG) after marginalisation over unobserved variables and conditioning on selection variables using the m-separation criterion. These include MC, summary, and ancestral grap…
Modof-pipe optimizes molecules by modifying a single site, outperforming state-of-the-art methods.
problem Improving drug candidates' properties through chemical modification.
method Deep generative model Modof over molecular graphs for molecule optimization.
result Modof-pipe achieves significant improvements in octanol-water partition coefficient and molecule similarity constraints.
Characterizes graphs with Lin-Lu-Yau curvature at least one and explores bone-idle graphs.
problem Characterizing graphs with specific curvature properties.
method Study of Ollivier-Ricci curvature and Lin-Lu-Yau curvature, exploration of regular graphs, and exact formula derivation.
result Characterizes edges that are bone-idle in regular graphs and provides a complete characterization of 4-regular bone-idle graphs.
PyTorch-BigGraph scales graph embeddings to large graphs.
problem Large graphs with billions of nodes and trillions of edges.
method Graph partitioning, multi-relation embedding system, distributed training.
result Comparable performance on benchmarks, scalable to large graphs.
Improved knowledge graph embedding using taxonomic information.
problem Learning about domains in knowledge graphs using embedding models.
method Minimal modifications to existing knowledge graph completion methods to incorporate taxonomic information.
result Our model is fully expressive, respecting subclass and subproperty information.
Unified model generates representations for all nodes in growing graphs.
problem Cold start problem in growing graphs isolates new nodes.
method Generative graph convolutional network that learns adaptive node representations.
result Superior performance on citation network datasets.
Recently, several data analytic techniques based on connection graph laplacian (CGL) ideas have appeared in the literature. At this point, the properties of these methods are starting to be understood in the setting where the data is observed without noise. We study the impact of additive noise on these methods, and sh…
Adding random features to GNNs improves their performance.
problem Limitations of GNNs in distinguishing graphs and learning efficient algorithms.
method Adding random features to each node in GNNs.
result Random features enable GNNs to learn optimal algorithms for graph problems.
Geo2DR learns graph representations using substructure patterns.
problem Learning distributed representations of graphs efficiently.
method Unsupervised learning with discrete substructure patterns and neural language models.
result Geo2DR achieves high reproducibility and interoperability in graph classification.
The paper explores new quandle systems for handlebody-links and spatial graphs.
problem Developing new invariants for handlebody-links and spatial graphs.
method Investigates and constructs new algebraic systems (quandles) to generalize existing ones.
result Provides necessary conditions for colouring invariants of knotted handlebodies.
The paper reformulates Bakry-Émery curvature on graphs using eigenvalues.
problem Analyzing curvature on weighted graphs.
method Reformulating curvature as the smallest eigenvalue of a rank one perturbation of the curvature matrix.
result The curvature function is analytic, strictly monotone increasing, and concave until a threshold, after which it is constant.
The paper tackles sparse graph learning under Laplacian-related constraints, improving upon existing methods.
problem Learning a sparse undirected graph from multivariate data under Laplacian-related constraints.
method Modifications to penalized log-likelihood approaches to enforce total positivity and lasso/adaptive lasso penalties using ADMM.
result The proposed constrained adaptive lasso approach significantly outperforms existing Laplacian-based approaches.
We solve minimal separator problems in AMP chain graphs and improve structure learning algorithms.
problem Finding minimal separators in AMP chain graphs and learning their structure from data.
method We analyze and solve several versions of the minimal separator problem. We propose modifications to the PC-like algorithm and extend a decomposition-based method for AMP CGs.
result Our modifications of the PC-like algorithm and the LCD-AMP method improve structure learning and are more accurate and stable, especially in high-dimensional settings.
Causal inference improves heterophilic graph learning.
problem Capturing asymmetric node dependencies in graph learning.
method Intervention-based causal inference for graph structure learning.
result CausalMP achieves superior link prediction performance.
Biological and social systems consist of myriad interacting units. The interactions can be represented in the form of a graph or network. Measurements of these graphs can reveal the underlying structure of these interactions, which provides insight into the systems that generated the graphs. Moreover, in applications s…
This work improves testing of machine learning model modifications using novel statistical methods.
problem Overfitting and conservative Bonferroni correction when testing multiple model modifications.
method Introduces alpha-recycling and SRGPs to control error rate and approve more beneficial modifications.
result Novel statistical methods approve a higher number of beneficial modifications than previous approaches.
The paper studies properties of Artin monoid Cayley graphs and their quasi-isometry to Deligne complexes.
problem Investigate properties of Artin monoid Cayley graphs.
method Show quasi-isometry to modified Deligne complex, address infinite diameter conjecture.
result Prove conjecture about infinite diameter for Artin groups containing specific subgroups.
We present a new algorithm for community detection. The algorithm uses random walks to embed the graph in a space of measures, after which a modification of k-means in that space is applied. The algorithm is therefore fast and easily parallelizable. We evaluate the algorithm on standard random graph benchmarks, inclu…
We investigate the problem of active learning on a given tree whose nodes are assigned binary labels in an adversarial way. Inspired by recent results by Guillory and Bilmes, we characterize (up to constant factors) the optimal placement of queries so to minimize the mistakes made on the non-queried nodes. Our query se…
LineMVGNN improves AML detection by integrating multi-view graph learning.
problem Ineffective and scalable AML systems using rule-based methods.
method LineMVGNN combines multi-view graph neural networks with line-graph features.
result LineMVGNN outperforms state-of-the-art methods in detecting money laundering.
Graph auto-encoders predict stock market instability by measuring graph structure changes.
problem Forecasting stock market instability and volatility.
method Use graph auto-encoders to reconstruct graph structure and measure changes.
result Higher GAE reconstruction error correlates with higher volatility.
Active Search has become an increasingly useful tool in information retrieval problems where the goal is to discover as many target elements as possible using only limited label queries. With the advent of big data, there is a growing emphasis on the scalability of such techniques to handle very large and very complex …
Valid prediction sets for dynamic graphs using conformal prediction.
problem Uncertainty quantification in dynamic graph neural networks.
method Dynamic graph unfolding for input to GNNs, combined with conformal prediction.
result Valid prediction sets with minimal assumptions, even in challenging scenarios.
Unified view on random walk and Weisfeiler-Leman kernels, improving accuracy.
problem Improving graph kernel methods for better classification accuracy.
method Define and analyze walk-based node refinement methods, relate to Weisfeiler-Leman test, and introduce new walk-based kernels.
result Walk-based kernels are as expressive as Weisfeiler-Leman subtree kernel but support non-strict neighborhood comparison.
We present a novel cost function for semi-supervised learning of neural networks that encourages compact clustering of the latent space to facilitate separation. The key idea is to dynamically create a graph over embeddings of labeled and unlabeled samples of a training batch to capture underlying structure in feature …
In 1993, Fenn, Rourke and Sanderson introduced rack spaces and rack homotopy invariants, and modifications to quandle spaces and quandle homotopy invariants were introduced by Nosaka in 2011. In this paper, we define the Cayley-type graph and the extended quandle space of a quandle in analogy to rack and quandle spaces…
We formulate a generalization of the volume conjecture for planar graphs. Denoting by <G, c> the Kauffman bracket of the graph G whose edges are decorated by real "colors" c, the conjecture states that, under suitable conditions, certain evaluations of <G,kc> grow exponentially as k goes to infinity and the growth rate…
PA-GNN enhances GNN robustness against poisoning attacks using clean graph knowledge.
problem Improving robustness of GNNs against poisoning attacks.
method PA-GNN uses a penalized aggregation mechanism and meta-optimization to transfer robustness from clean graphs.
result PA-GNN significantly improves GNN robustness against poisoning attacks on real-world graphs.
New method detects RNA modifications without prior training, revealing novel sites.
problem Detecting RNA modifications with high accuracy and sensitivity.
method Anomaly detection using nanopore raw ionic current signals and nearest neighbor comparison.
result Detects diverse RNA modifications without prior training, including a novel 2'-O-methylated site in DENV.
Paper tackles order-dependence in structure learning of multivariate regression chain graphs.
problem Order-dependence in structure learning of multivariate regression chain graphs.
method Proposes modifications to the PC-like algorithm to remove order-dependence.
result Improved performance in high-dimensional settings with modifications to the PC-like algorithm.
We define an operation on homology B4 which we call an n-twist annulus modification. We give a new construction of smoothly slice knots and exotically slice knots via n-twist annulus modifications. As an application, we present a new example of a smoothly slice knot with non-slice derivatives. Such examples we…
Optimizes ground metric on graphs for evolving density models.
problem Optimizing ground metric for evolving density models.
method Adaptive ground metric learning constrained to geodesic distances on graphs.
result Efficiently learned geodesic distances align with observed density evolution.
In this paper, we consider the problem of estimating the underlying graph associated with an Ising model given a number of independent and identically distributed samples. We adopt an \emph{approximate recovery} criterion that allows for a number of missed edges or incorrectly-included edges, in contrast with the widel…