Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

85170254339 · Jun 202019922001200920172026
48 results for graph patterns

HYPA-DBGNN detects anomalous sequential patterns in temporal graphs.

problem Modeling temporal patterns in dynamic graphs, especially considering deviations from random shuffling.
method Two-step approach combining null model inference and neural message passing.
result HYPA-DBGNN outperforms baseline methods in static node classification tasks.

We establish a correspondence between the dimer model on a bipartite graph and a circle pattern with the combinatorics of that graph, which holds for graphs that are either planar or embedded on the torus. The set of positive face weights on the graph gives a set of global coordinates on the space of circle patterns wi…

2018-10-12abs ↗pdf ↗

A new kernel measures brain network similarities, improving disease classification.

problem Lack of edge weight information in existing graph kernels for brain connectivity networks.
method Ordinal pattern kernel for weighted brain connectivity networks.
result The ordinal pattern kernel achieves better classification performance than state-of-the-art graph kernels.

GraphSTONE uses topic models to capture graph structures, improving GCN performance.

problem GCNs focus too much on node features and not enough on graph structures.
method GraphSTONE employs topic models of graphs to capture structural topics, which guide the aggregation of node features.
result GraphSTONE outperforms GCNs in performance, efficiency, and interpretability.

Graph Neural Networks improve financial time series forecasting accuracy.

problem Forecasting univariate financial time series with statistical significance.
method Introducing the Time-Geometric model combining geometric and temporal patterns.
result Statistically significant improvements in forecasting accuracy through geometric patterns.

GraphDETR detects subgraphs in large graphs using deep learning.

problem Detecting subgraphs in large graphs efficiently and accurately.
method Formulates subgraph detection as a set prediction problem using GraphDETR, a deep learning framework.
result GraphDETR can detect diverse patterns in large graphs, achieving strong performance on molecular functional group detection.

Sequences of correlated binary patterns can represent many time-series data including text, movies, and biological signals. These patterns may be described by weighted combinations of a few dominant structures that underpin specific interactions among the binary elements. To extract the dominant correlation structures …

2019-01-22abs ↗pdf ↗

GraphQ system uses GNNs to search for subgraph patterns in graphs.

problem Efficiently identifying and matching subgraph patterns in graph data.
method Graph neural networks (GNNs) for encoding graph data and NeuroAlign for node alignment.
result NeuroAlign improves node-alignment accuracy by 19-29% compared to baseline GNNs.

Fine-tunes GNNs by preserving generative patterns to improve transferability.

problem Vanilla fine-tuning fails due to structural divergence between pre-training and downstream graphs.
method G-Tuning, which reconstructs the generative patterns of the downstream graph using graphon bases.
result G-Tuning achieves an average improvement of 0.5% and 2.6% on in-domain and out-of-domain transfer learning experiments.

Proposes a method to infer complex network topologies from multiple graphs.

problem Learning multiple graph Laplacian matrices from heterogeneous graph signals with intricate topological patterns.
method Structured fusion regularization and ADMM algorithm for efficient computation.
result Establishes a non-asymptotic bound of the estimation error and reflects the effect of key factors on convergence rate.

It is not until recently that graph neural networks (GNNs) are adopted to perform graph representation learning, among which, those based on the aggregation of features within the neighborhood of a node achieved great success. However, despite such achievements, GNNs illustrate defects in identifying some common struct…

2019-11-18abs ↗pdf ↗

Method analyzes large-scale network data to detect communication pattern shifts.

problem Analyzing large-scale time-series network data is challenging.
method Temporal encoder embedding method using ground-truth or estimated vertex labels.
result Detects communication pattern shifts across all levels of network structure.

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.

node2coords learns interpretable graph node representations robust to graph perturbations.

problem Need representations that capture graph structure and are robust to perturbations.
method Proposes a graph representation learning algorithm using Wasserstein barycenters.
result Learned representations are interpretable and stable to graph perturbations.

FEALM learns features for better nonlinear DR of hidden patterns.

problem DR misses important patterns on distorted manifolds.
method FEALM generates optimized projections using an optimization algorithm and neighbor-shape dissimilarity.
result FEALM captures important patterns on hidden manifolds.

A novel method uses blockchain transaction graphs for Bitcoin price prediction.

problem Insufficient effectiveness of manually designed features for Bitcoin price prediction.
method Mining patterns from Bitcoin transactions using k-order transaction graphs and proposing a novel prediction method.
result The proposed method outperforms state-of-the-art Bitcoin price prediction methods.

A ``hyperideal circle pattern'' in S2S^2 is a finite family of oriented circles, similar to the ``usual'' circle patterns but such that the closed disks bounded by the circles do not cover the whole sphere. Hyperideal circle patterns are directly related to hyperideal hyperbolic polyhedra, and also to circle packings. …

2004-07-03abs ↗pdf ↗

AGCRN forecasts traffic using adaptive graph and recurrent learning.

problem Forecasting traffic dynamics with complex spatial and temporal correlations.
method Adaptive Graph Convolutional Recurrent Network (AGCRN) with Node Adaptive Parameter Learning (NAPL) and Data Adaptive Graph Generation (DAGG).
result AGCRN outperforms state-of-the-art models without pre-defined graphs.

The paper explores how different patterns of heterophily affect Graph Neural Networks.

problem Understanding the impact of heterophily on Graph Neural Networks.
method Theoretical analysis and experiments with Heterophilous Stochastic Block Models (HSBM).
result The impact of heterophily on classification depends on the Euclidean distance of neighborhood distributions and the averaged node degree.

Auto-decoder synthesizes graphs from latent codes.

problem Creating new graph structures from specified distributions.
method Generative model learns latent codes from empirical distribution. Self-attention identifies likely connectivity patterns. Graph-based normalizing flows sample latent codes.
result Model outperforms state of the art by 1.5x in accuracy and 2x in speed.

In this paper, we study a new graph learning problem: learning to count subgraph isomorphisms. Different from other traditional graph learning problems such as node classification and link prediction, subgraph isomorphism counting is NP-complete and requires more global inference to oversee the whole graph. To make it …

2019-12-25abs ↗pdf ↗

CMC-1 surfaces linked via Möbius transformations between circle patterns.

problem Characterizing and relating CMC-1 surfaces via circle patterns.
method Osculating Möbius transformations between circle patterns induce realizations in hyperbolic space.
result One-to-one correspondence between CMC-1 surfaces under specific conditions.

Graphs model human mobility patterns, reducing errors in data matching.

problem Lack of high-quality data and computational resources for graph-based mobility analysis.
method Embedding graphs into a continuous space to address matching, modeling, and visualization challenges.
result Approx 40% decrease in error on average in matched graphs vs unmatched ones.

New guarantees for matrix completion from any deterministic sampling patterns.

problem Proving guarantees for low-rank matrix completion from non-random sampling schemes.
method Introduced a graph with observed entries as edges to analyze the performance of constrained nuclear norm minimization algorithm.
result The algorithm can successfully complete the matrix if the observation graph is well-connected and has similar node degrees.

This work improves KG embeddings by integrating hyperbolic and attention mechanisms.

problem Preserving hierarchical and logical patterns in KGs with low-dimensional embeddings.
method Combines hyperbolic reflections/rotations with attention mechanisms to capture complex relational patterns.
result Improves MRR by up to 6.1% on standard benchmarks and new state-of-the-art results in high dimensions.

Interaction graphs, such as those recording emails between individuals or transactions between institutions, tend to be sparse yet structured, and often grow in an unbounded manner. Such behavior can be well-captured by structured, nonparametric edge-exchangeable graphs. However, such exchangeable models necessarily ig…

2019-05-28abs ↗pdf ↗

Leighton's graph covering theorem states that a pair of finite graphs with isomorphic universal covers have a common finite cover. We provide a new proof of Leighton's theorem that allows generalizations; we prove the corresponding result for graphs with fins. As a corollary we obtain pattern rigidity for free groups w…

2018-06-21abs ↗pdf ↗

In this paper, we propose a new feature extraction technique for program execution logs. First, we automatically extract complex patterns from a program's behavior graph. Then, we embed these patterns into a continuous space by training an autoencoder. We evaluate the proposed features on a real-world malicious softwar…

2018-04-10abs ↗pdf ↗

Calendar graph neural networks model user behavior with location and time data.

problem Modeling user behavior with location and time information for demographic prediction.
method Graph neural networks with a tripartite network of items, sessions, and locations, and a hierarchical calendar network.
result User embeddings preserve spatial and temporal patterns of various periodicity.

In sparse signal representation, the choice of a dictionary often involves a tradeoff between two desirable properties -- the ability to adapt to specific signal data and a fast implementation of the dictionary. To sparsely represent signals residing on weighted graphs, an additional design challenge is to incorporate …

2014-01-05abs ↗pdf ↗

The paper develops finite knot theory using ropelength-filtered Reidemeister graphs.

problem Understanding knot types in bounded ropelength sublevel spaces.
method Study thick representatives in bounded ropelength sublevel spaces through lifted Reidemeister graphs.
result Define characteristic Reidemeister patterns and finite recognition length.

Khovanov homology of a link and chromatic graph homology are known to be isomorphic in a range of homological gradings that depend on the girth of a graph. We discuss patterns shared by these two homology theories. In particular, we improve the bounds for the homological span of chromatic homology by Helme-Guizon, Przy…

2018-01-04abs ↗pdf ↗