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.

168,695 papers · 148 categories

Trend · papers per month

105211316421 · Jun 202019922001200920172026
48 results for graph transformers

Line graph transformation aids graph isomorphism tests by excluding challenging graph properties.

problem Limited theoretical understanding of line graph transformation's impact on GNN models.
method Examined CFI and strongly regular graphs, showing line graph transformation helps WL tests distinguish these graphs.
result Line graph transformation aids WL tests in distinguishing challenging graph properties.

PatchGT uses non-trainable graph patches to improve graph representation learning.

problem Learning high-level information in graph tasks with direct Transformer models.
method PatchGT segments graphs into non-trainable patches, uses GNN for patch-level learning, and Transformer for graph-level learning.
result PatchGT achieves higher expressiveness and competitive performance on benchmark datasets.

We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform. Different from graph Fourier transform, graph wavelet transform can be obtained …

2019-04-12abs ↗pdf ↗

Graph transformers outperform graph convolutions by preserving community information.

problem Understanding why graph transformers perform well in node-level prediction tasks.
method Analyzing the Gaussian process limits of graph transformers with infinite width and infinite heads.
result Graph transformers maintain discriminative node representations even in deep layers, preventing oversmoothing.

Many signals on Cartesian product graphs appear in the real world, such as digital images, sensor observation time series, and movie ratings on Netflix. These signals are "multi-dimensional" and have directional characteristics along each factor graph. However, the existing graph Fourier transform does not distinguish …

2017-12-21abs ↗pdf ↗

Transformer adapts to graphs with adaptive attention and auto-regressive decoding.

problem Transformers struggle with graph data due to non-sequential nature.
method Proposes GRAT, a Transformer variant with adaptive attention and auto-regressive decoding.
result GRAT achieves state-of-the-art performance on molecule property predictions and generation tasks.

This thesis explores GNNs, categorizing them into local and global approaches.

problem Understanding the convergence of global GNNs and connecting local and global approaches.
method Categorization of GNNs into local and global, study of Invariant Graph Networks, connecting local and global approaches, and using local MPNN for graph coarsening.
result Established a connection between local and global GNN approaches.

RP-GFRFT unifies fractional order and rotation control for graph signals.

problem Lack of rotation-based spectral control in GFRFT and zero-angle degeneracy in AGFT.
method Rotation-parameterized graph fractional Fourier transform (RP-GFRFT) with degeneracy preserving rotation matrix.
result RP-GFRFT improves spectral filtering performance over 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 ↗

Scattering transforms are non-trainable deep convolutional architectures that exploit the multi-scale resolution of a wavelet filter bank to obtain an appropriate representation of data. More importantly, they are proven invariant to translations, and stable to perturbations that are close to translations. This stabili…

2019-06-11abs ↗pdf ↗

IGT learns graph representations without supervision.

problem Building deep unsupervised graph representations.
method Generic complex-valued spectral graph architecture from Fourier transform generalization, greedy concave objective for discriminative and invariant features.
result IGT learns both discriminative and invariant features from graph topology.

Holonomy-preserving transformations help recover Alexander polynomials from graph zeta functions.

problem Recovering Alexander polynomials from graph zeta functions.
method Introducing holonomy to preserve zeta functions of matrix-weighted graphs and extending to group elements and quandles.
result Holonomy-preserving transformations correspond to transformations of group presentations and preserve the twisted Alexander polynomial.

We introduce a transformer-based GNN model, named UGformer, to learn graph representations. In particular, we present two UGformer variants, wherein the first variant (publicized in September 2019) is to leverage the transformer on a set of sampled neighbors for each input node, while the second (publicized in May 2021…

2019-09-26abs ↗pdf ↗

Transformers interpreted as probabilistic Laplacian Eigenmaps steps.

problem Improving transformer performance through probabilistic interpretation.
method Probabilistic Laplacian Eigenmaps model derivation and graph diffusion step.
result Subtracting identity from attention matrix improves transformer performance.

The study finds conditions for compressing the hidden dimension of Graph Transformers for transductive learning.

problem The challenge of efficiently analyzing and training Graph Transformers for transductive learning.
method Theoretical bounds on hidden dimension compression for Graph Transformers, considering both sparse and dense variants.
result Theoretical findings on how and under what conditions the hidden dimension of Graph Transformers can be compressed.

Paper classifies minimal graph transformations into new families of surfaces.

problem Classifying minimal graph transformations into new families of surfaces.
method Formulated and solved a coupled system of partial differential equations, reduced to solving an ordinary differential equation.
result Established rigorous equivalence to a modified problem for a harmonic function, yielding new families of minimal surfaces.

IsoGCNs learn invariant and equivariant graph features for efficient simulations.

problem Learning isometric transformation invariant and equivariant features in graphs for simulations.
method Transformation invariant and equivariant Graph Convolutional Networks (IsoGCNs).
result IsoGCNs outperform state-of-the-art methods on geometrical and physical simulation tasks.

A new method reduces memory requirements for Graph Transformers by sparsely training a network.

problem Quadratic memory complexity in Graph Transformers limits their scalability to large graphs.
method Spexphormer: trains a narrow network on augmented graph, then uses only active connections in a wider network.
result Spexphormer achieves good performance with drastically reduced memory requirements.

In the following text we prove that for all finite p0p\geq0 there exists a topological graph XX such that {p,p+1,p+2,}{+}\{p,p+1,p+2,\ldots\}\cup\{+\infty\} is the collection of all possible heights for transformation groups with phase space XX. Moreover for all topological graph XX with pp as height of transformation group $(H…

2017-10-30abs ↗pdf ↗

FairGP uses graph partitioning to make Graph Transformers fair and scalable.

problem Fairness issues in Graph Transformers, especially against sensitive features.
method Graph partitioning to minimize the influence of higher-order nodes and optimize attention mechanisms.
result FairGP improves fairness in Graph Transformers while reducing computational complexity.

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.

Transformer model pretrains on synthetic graphs for AD detection.

problem Limited labeled data and class imbalance in AD diagnosis.
method Diffusion-generated synthetic graphs, Graph Transformers, transfer learning.
result Framework outperforms baselines in AD diagnosis metrics.

Geometrically, Legendrian surfaces related by surgery have related skein-valued cluster spaces.

problem Understanding the skein-valued cluster transformation in Legendrian surfaces.
method Geometric considerations of moduli of holomorphic curves.
result Skein-valued cluster transformation of Legendrian surfaces related by surgery.

A new method for graph-structured data improves transformer performance by incorporating topology.

problem Improving transformer performance on graph-structured data.
method Parameterizing topological masks as a learnable function of a weighted adjacency matrix, approximated with graph random features.
result Efficient masking algorithms provide strong performance gains for tasks on image and point cloud data.

In many state-of-the-art compression systems, signal transformation is an integral part of the encoding and decoding process, where transforms provide compact representations for the signals of interest. This paper introduces a class of transforms called graph-based transforms (GBTs) for video compression, and proposes…

2019-09-03abs ↗pdf ↗

CT improves neural network performance on cell complex data.

problem Improving predictive performance of neural networks on complex data.
method Introducing the Cellular Transformer (CT) that generalizes graph-based transformers to cell complexes.
result CT achieves state-of-the-art performance on cell complex datasets without complex enhancements.

Efficiently approximates eigenspaces for symmetric and general matrices.

problem Fast computation of eigenspaces for large matrices.
method Factor eigenspaces into fundamental components using transformations, solve minimization problems, and iteratively update.
result Improved computational efficiency for eigenspace approximation.

In many video coding systems, separable transforms (such as two-dimensional DCT-2) have been used to code block residual signals obtained after prediction. This paper proposes a parametric approach to build graph-based separable transforms (GBSTs) for video coding. Specifically, a GBST is derived from a pair of line gr…

2019-11-16abs ↗pdf ↗

Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especial…

2019-11-06abs ↗pdf ↗

HGT models heterogeneous graphs with dedicated node and edge representations.

problem Infeasibility of existing GNNs for heterogeneous graphs.
method Node- and edge-type dependent parameters, relative temporal encoding, heterogeneous mini-batch graph sampling.
result HGT outperforms state-of-the-art GNNs by 9%--21% on various downstream tasks.

We explore the generalization of scattering transforms from traditional (e.g., image or audio) signals to graph data, analogous to the generalization of ConvNets in geometric deep learning, and the utility of extracted graph features in graph data analysis. In particular, we focus on the capacity of these features to r…

2018-10-07abs ↗pdf ↗

G2Gs transforms target molecules into reactants without templates, improving accuracy.

problem Predicting retrosynthesis from target molecules efficiently and accurately.
method Transforming target molecular graphs into reactant graphs via variational graph translation.
result G2Gs achieves top-1 accuracy close to state-of-the-art template-based methods.

Paper forecasts stock correlations using a hybrid model combining graph neural networks and transformers.

problem Improving stock correlation forecasts for better portfolio management.
method Hybrid model combining Transformer and graph attention networks for forecasting residual deviations from historical data.
result The hybrid model reduces correlation forecasting error compared to rolling-window estimates.

Much of the recent work on learning molecular representations has been based on Graph Convolution Networks (GCN). These models rely on local aggregation operations and can therefore miss higher-order graph properties. To remedy this, we propose Path-Augmented Graph Transformer Networks (PAGTN) that are explicitly built…

2019-05-29abs ↗pdf ↗

The paper refines transformations of lattice diagrams and introduces dotted diagrams.

problem Investigating transformations and deformations of lattice diagrams and their associated dotted diagrams.
method Introducing dotted diagrams and investigating deformations of these diagrams, relating them to transformations of lattice diagrams.
result Refined results on the relation between deformations of admissible dotted diagrams and transformations of lattice diagrams.

The paper proves a stability result for translating space-like graphs in Lorentz manifolds.

problem Investigating stability of translating space-like graphs in Lorentz manifolds.
method Analyzing space-like graphs over a domain in Lorentz manifold with a specific metric and proving stability under conformal transformation.
result An interesting stability result for translating space-like graphs in MnimesRM^{n} imes\mathbb{R} is proven.

SE(3)-Transformers maintain equivariance for 3D data under rotations and translations.

problem Ensuring stable and predictable performance in 3D data under transformations.
method Introducing a self-attention module that is equivariant under continuous 3D roto-translations.
result The SE(3)-Transformer outperforms non-equivariant and non-attention models on real-world datasets.