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.

168,694 papers · 148 categories

Trend · papers per month

83165248330 · Jun 202019922001200920172026
48 results for fine graphs

New findings on hyperbolicity of fine curve graphs and their subgraphs.

problem Investigating hyperbolicity of fine curve graphs and their subgraphs.
method Analyzing large subgraphs of fine curve graphs and computing distances in specific cases.
result Large subgraphs of fine curve graphs contain flats of every finite dimension, indicating they are not hyperbolic.

The fine curve graph is hyperbolic and contains all countable graphs as induced subgraphs.

problem Characterizing the structure and properties of fine curve graphs.
method Analyzing the hyperbolicity and induced subgraph properties of fine curve graphs and their direct limits.
result The finitary curve graph has diameter 2, contains every countable graph as an induced subgraph, and has the homeomorphism group of the surface as its automorphism group.

Automorphisms of fine curve graphs match surface homeomorphisms for planar surfaces.

problem Understanding automorphisms of fine curve graphs on surfaces.
method Analyzing vertices and edges of fine curve graphs to match with surface homeomorphisms.
result Automorphism group of fine curve graphs is naturally isomorphic to the homeomorphism group of boundaryless planar surfaces with at least 7 punctures.

The paper studies the connectedness of a graph's boundary for surfaces.

problem Understanding the topology of the Gromov boundary of fine curve graphs for surfaces.
method Proved a bounded geodesic image theorem, used to show linear connectivity of the Gromov boundary.
result The Gromov boundary of fine curve graphs for surfaces is linearly connected.

Automorphism group of nonorientable surface curve graph matches surface homeomorphisms.

problem Identifying automorphisms of nonorientable surface curve graphs.
method Using Bowden, Hensel, and Webb's fine curve graph and Long, Margalit, Pham, Verberne, and Yao's proof as a foundation.
result Automorphism group of nonorientable surface curve graph is isomorphic to the surface's homeomorphism group.

Characterizes geometric actions on graphs with flexible stabilizers.

problem Understanding geometric actions on flexible stabilizers.
method Defining generalized fine actions and proving relative quasi-convexity criteria.
result Characterizes Bowditch boundary points in relatively geometric actions.

The study proves conditions for hyperbolic isometries on fine curve graphs of higher genus surfaces.

problem Conditions for hyperbolic isometries on fine curve graphs of higher genus surfaces.
method Proves equivalence of conditions involving isotopic maps, pseudo-Anosov maps, and ergodic rotation sets.
result Ergodic homological rotation sets have nonempty interior for certain isotopic maps.

Stable cylinders found in hyperbolic groups and curve graphs.

problem Torsionfree hyperbolic groups and curve graphs of surfaces have globally stable cylinders.
method Generalised Sageev's construction to improve fine properties of hyperbolic spaces.
result Proved curve graphs of surfaces admit equivariant quasi-isometric embeddings in finite products of quasitrees.

Abstract: Proves generic torus diffeomorphisms act parabolically and non-properly on fine curve graph and have generalized rotation sets.

problem Generic torus diffeomorphisms on fine curve graph.
method Proves generic torus diffeomorphisms act parabolically and non-properly on fine curve graph.
result Generic torus diffeomorphisms have generalized rotation sets of any point-symmetric compact convex homothety type.

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.

New framework learns labels at both bag and graph levels.

problem Learning multi-label classifiers from multi-graph bags.
method Designing scoring functions and rank-loss objective for graph and bag levels; developing sub-gradient descent algorithm.
result Superior performance over state-of-the-art algorithms.

Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to tr…

2019-02-14abs ↗pdf ↗

A new neural network model for molecular graphs that learns efficiently and accurately.

problem Learning on molecular graphs with cycles and complex structures.
method Hierarchical inter-message passing using raw graph and junction tree representations.
result The model outperforms classical GNNs in detecting cycles and is efficient to train.

Study homeomorphisms on fine curve graph of surfaces, revealing new types of dynamics.

problem Understanding dynamics of homeomorphisms on fine curve graphs of surfaces.
method Analyzing the action of homeomorphisms on the fine curve graph and relating to classical curve graphs.
result Homeomorphisms induce parabolic isometries, and all positive reals are realized as asymptotic translation lengths.

The paper proposes DEA to make graph neural networks fairer in link prediction.

problem Graph neural networks can unfairly prioritize certain social groups in link prediction.
method Drop Edges and Adapt (DEA) fine-tuning strategy with covariance constraints.
result DEA improves fairness and accuracy in link prediction tasks.

Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significan…

2020-02-08abs ↗pdf ↗

PSimGNN partitions graphs into subgraphs for efficient graph similarity computation.

problem Efficiently compute graph similarity scores for large graphs.
method Graph partitioning followed by subgraph-level and node-level comparisons using a graph neural network.
result PSimGNN outperforms state-of-the-art methods in graph similarity computation tasks.

Study on stable translation lengths of surface homeomorphisms and their approximations.

problem Understanding stable translation lengths of homeomorphisms and their finite approximations.
method Comparing stable translation lengths of homeomorphisms and their finite approximations on curve graphs.
result Stable translation length of homeomorphisms with dense periodic points equals the supremum of their approximations.

ADSAGE detects anomalies in graph edge sequences for insider threat detection.

problem Detecting insider threats in fine-grained audit logs using graph and text features.
method Anomaly detection at edge level, supporting numeric, categorical, and text attributes.
result ADSAGE detects anomalies in authentications and email communications effectively.

PanRep learns universal node embeddings for heterogeneous graphs.

problem Learning universal node embeddings for heterogeneous graphs.
method Graph Neural Network (GNN) model with four decoders capturing different properties.
result PanRep outperforms unsupervised and supervised methods in node classification and link prediction.

Heterogeneous GNN improves species distribution modeling.

problem Predicting species occurrences and habitat suitability using environmental factors.
method Graph Neural Networks (GNN) for presence-only species distribution modeling.
result Heterogeneous GNN model outperforms single-species SDMs and baseline models.

SGQuant reduces GNN memory usage without significant accuracy loss.

problem High memory consumption in GNNs limits their applicability on memory-constrained devices.
method Proposes a specialized GNN quantization scheme (SGQuant) with a quantization algorithm, fine-tuning scheme, and multi-granularity strategy.
result SGQuant reduces GNN memory footprint from 4.25x to 31.9x with minimal accuracy loss.

Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.

problem LLMs struggle with financial NER, especially differentiating entities and amounts.
method Instruction fine-tuning combined with LoRA for parameter-efficient learning.
result Micro-F1 score of 0.894 on financial NER tasks, outperforming other models.

Automorphisms and subdivisions of Helly graphs are studied, leading to explicit models and rational translation lengths.

problem Understanding automorphisms and subdivisions of Helly graphs.
method Simple fine simplicial subdivisions and explicit simplicial models of the injective hull.
result Any automorphism of a Helly graph is either elliptic or hyperbolic, with rational translation lengths.

We explore the combination theorem for a group G splitting as a graph of relatively hyperbolic groups. Using the fine graph approach to relative hyperbolicity, we find short proofs of the relative hyperbolicity of G under certain conditions. We then provide a criterion for the relative quasiconvexity of a subgroup H de…

2012-11-08abs ↗pdf ↗

SpeqNets improve graph neural networks by scaling and adapting to graph sparsity.

problem Graph neural networks struggle with permutation-equivariant functions and scalability to large graphs.
method Introducing sparsity-aware, permutation-equivariant graph networks with heuristics for graph isomorphism.
result Significantly improved predictive performance and reduced computation times compared to existing methods.

Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which GNNs adapt to input graphs of varying size and structure. We propose a new graph pooling operation based on compressive Haar transforms -- HaarPo…

2019-09-25abs ↗pdf ↗

Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from molecules and materials to RNA secondary structures. Several kernel functions have been defined on graphs that coupled with kernelized learn…

2018-11-16abs ↗pdf ↗

Improved graph neural network bounds using graph diffusion matrix.

problem Empirical performance of graph neural networks on real-world graphs.
method Unified model of graph neural networks, focusing on feature diffusion matrix stability.
result Generalization bounds scale with largest singular value of feature diffusion matrix, smaller than prior bounds.

New algorithm estimates task affinities without repeated training, improving model performance and efficiency.

problem Efficiently estimating task affinities among multiple tasks for model training.
method Grad-TAG algorithm: trains a base model for all tasks and uses gradient-based linearization to estimate task affinities.
result Estimates task affinities with high accuracy and low computational cost.

Graph-structured data arise ubiquitously in many application domains. A fundamental problem is to quantify their similarities. Graph kernels are often used for this purpose, which decompose graphs into substructures and compare these substructures. However, most of the existing graph kernels do not have the property of…

2020-02-23abs ↗pdf ↗

AutoGraph uses transformers to efficiently generate graphs as sequences.

problem Efficiently generating large, sparse graphs without expensive node features.
method Flattening graphs into sequences and using decoder-only transformers.
result AutoGraph achieves state-of-the-art performance on synthetic and molecular benchmarks.

In graph instance representation learning, both the diverse graph instance sizes and the graph node orderless property have been the major obstacles that render existing representation learning models fail to work. In this paper, we will examine the effectiveness of GRAPH-BERT on graph instance representation learning,…

2020-02-09abs ↗pdf ↗