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

213426638851 · Jun 202019922001200920172026
48 results for interpretable edge functions

Temporal Functional Circuits explain KAN forecasts with interpretable edge functions.

problem Lack of mechanistic explanations in KAN forecasting.
method Transform KAN edge functions into faithful, temporally grounded explanations using a gated residual KAN.
result Gated KAN achieves lower MSE than linear-only models on regime-switching signals.

Functional connections in the brain are frequently represented by weighted networks, with nodes representing locations in the brain, and edges representing the strength of connectivity between these locations. One challenge in analyzing such data is that inference at the individual edge level is not particularly biolog…

2019-03-06abs ↗pdf ↗

GISST interprets GNNs by combining attention and sparsity for graph structure and node feature importance.

problem Lack of joint consideration of graph structure and node features in GNN interpretation.
method Model-agnostic framework using attention mechanism and sparsity regularization.
result GISST achieves superior node feature and edge explanation precision in synthetic and real-world datasets.

We construct a function of the edge-lengths of a triangulated surface whose variation under a rescaling of all the edges that meet at a vertex is the defect angle at that vertex. We interpret this function as a gravitational effective action on the triangulation, and the variation as a trace anomaly.

2005-12-22abs ↗pdf ↗

Researchers develop a method to interpret GNNs by identifying unnecessary edges in NLP models.

problem Understanding which parts of graphs contribute to NLP model predictions.
method A post-hoc method using differentiable edge masking to identify and drop unnecessary edges.
result Large proportions of edges can be dropped without affecting model performance, providing insights into model predictions.

KANs replace fixed MLP weights with learnable edge functions, improving accuracy and interpretability.

problem Lack of interpretability and scalability in MLPs.
method KANs use learnable activation functions on edges instead of fixed weights, replacing weights with spline functions.
result KANs outperform MLPs in accuracy and interpretability with smaller models.

BetaExplainer improves GNN interpretability by masking unimportant edges.

problem Interpreting GNNs' predictions is difficult due to black-box behavior and lack of uncertainty quantification.
method BetaExplainer uses a sparsity-inducing prior to mask unimportant edges during training.
result BetaExplainer provides uncertainty in edge importance and improves predictive accuracy on challenging datasets.

We show that an appropriate generalization of the oriented area function is a perfect Morse function on the space of three-dimensional configurations of an equilateral polygonal linkage with odd number of edges. Therefore cyclic equilateral polygons (which appear as Morse points) are interpreted as independent generato…

2016-11-14abs ↗pdf ↗

This paper interprets critical scales in persistent homology for compact metric spaces.

problem Understanding critical scales in persistent homology for general compact metric spaces.
method Analyzing local minima of the distance function and their impact on persistence.
result Each decrease in zero-dimensional persistence and increase in one-dimensional persistence is induced by local minima of the distance function.

Proposes a method to improve GNN predictions by finding the most predictive subgraph.

problem GNNs aggregate all nodes and edges, making predictions hard to interpret.
method Uses reinforcement learning to find a sparse subgraph that optimizes graph classification performance.
result Our method finds sparser subgraphs that improve interpretability while maintaining performance.

We model microbiome interactions as graphs to interpret complex dynamics.

problem Understanding the differences in microbiome profiles between healthy and ill individuals.
method Developed a method to learn low-dimensional graph representations of time-evolving microbiome interactions.
result Extracted graph features that highlight microbes and interactions strongly correlated with clinical diseases.

We try to give a cluster algebraic interpretation of complex volume of knots. We construct the R-operator from the cluster mutations, and we show that it is regarded as a hyperbolic octahedron. The cluster variables are interpreted as edge parameters used by Zickert in computing complex volume.

2013-04-17abs ↗pdf ↗

New method uses Ricci curvature for hypergraph clustering, outperforming existing techniques.

problem Community detection in hypergraphs with large hyperedges.
method Extending Ricci flow to hypergraphs by defining edge probability measures and transporting them on the line expansion.
result Enhanced sensitivity to hypergraph structure, especially in large hyperedges.

SVGP KAN integrates sparse variational GP with KANs for scalable probabilistic inference.

problem Lack of probabilistic outputs in standard KANs and cubic scaling of Gaussian Process methods.
method Sparse Variational GP-KAN combines KAN topology with sparse variational inference and permutation-based importance analysis.
result Enables probabilistic KANs to handle larger datasets with linear computational complexity.

While statistical analysis of a single network has received a lot of attention in recent years, with a focus on social networks, analysis of a sample of networks presents its own challenges which require a different set of analytic tools. Here we study the problem of classification of networks with labeled nodes, motiv…

2017-01-27abs ↗pdf ↗

The {\em Wiman-Edge pencil} is the universal family $\Cs/\mathcal B$ of projective, genus 66, complex-algebraic curves admitting a faithful action of the icosahedral group $\Af_5$. The goal of this paper is to prove that the monodromy of $\Cs/\mathcal B$ is commensurable with a Hilbert modular group; in particular is …

2019-11-04abs ↗pdf ↗

Herding defines a deterministic dynamical system at the edge of chaos. It generates a sequence of model states and parameters by alternating parameter perturbations with state maximizations, where the sequence of states can be interpreted as "samples" from an associated MRF model. Herding differs from maximum likelihoo…

2016-02-09abs ↗pdf ↗

In this paper we characterize a function defined on the set of edges of a triangulated surface such that there is a spherical angle structure having the function as the edge invariant (or Delaunay invariant). We also characterize a function such that there is a hyperbolic angle structure having the function as the edge…

2006-01-20abs ↗pdf ↗

New framework for disentangling graph node and edge features.

problem Learning disentangled representations for attributed graphs with node and edge features.
method Proposes a novel variational objective and architecture for node and edge deconvolutions to disentangle latent factors.
result Demonstrates effectiveness of the proposed model and its extensions on synthetic and real-world datasets.

New model for network analysis using functional data.

problem Existing network models treat nodes as functions, but this paper introduces functional edges.
method Transform adjacency matrix into functional adjacency tensor, apply Tucker decomposition, regularize basis matrices, and solve tensor completion problem.
result The model effectively captures community structure and handles irregular functional edge data.

Bayesian neural networks learn graph structure with interpretable parameters.

problem Learning graph structure from nodal observations in data with uncertainty.
method Introduces novel iterations with independently interpretable parameters and Bayesian neural networks.
result Bayesian neural networks provide well-calibrated uncertainty quantification on graph structure.

This study explores how feature graphs enhance GNNs' performance in modeling interactions.

problem Improving GNNs' ability to model feature interactions effectively.
method Investigates feature graphs and their importance in GNNs, using experiments and theoretical support.
result Edges between interacting features are crucial for GNNs, while non-interaction edges can degrade performance.

Method estimates heterogeneous causal effects on networks using orthogonal learning.

problem Challenges in estimating causal effects on networks due to treatment effects on both treated and neighbors, and network homophily.
method Two-stage orthogonal learning framework: first stage uses graph neural networks for nuisance components, second stage residualizes and interpretable attention-based model for causal effects.
result Improves heterogeneous effect estimation and supports interpretable analyses.

Paper proposes forecast-necessity testing for accurate causal interpretation in nonlinear time-series models.

problem Misinterpretation of causal scores from nonlinear models as regression coefficients.
method Systematic edge ablation and forecast comparison to evaluate causal necessity.
result Causal relationships with similar scores can differ in their necessity for accurate prediction.

Gradient descent near stability threshold exhibits sharpness oscillations.

problem Understanding sharpness behavior near stability threshold in non-Euclidean norms.
method Interpreted EoS through Directional Smoothness and generalized sharpness under arbitrary norms.
result Non-Euclidean GD with generalized sharpness shows sharpness oscillations near 2/η2/η.

Community detection is an important task in network analysis, in which we aim to learn a network partition that groups together vertices with similar community-level connectivity patterns. By finding such groups of vertices with similar structural roles, we extract a compact representation of the network's large-scale …

2014-04-02abs ↗pdf ↗

This paper studies communication efficiency in federated learning by optimizing the sum-rate-distortion function for indirect multiterminal source coding.

problem Indirect multiterminal source coding in federated learning where edge devices send noisy gradients to the server.
method Analyzes the rate region for the quadratic vector Gaussian CEO problem under unbiased estimator and derives an explicit formula for the sum-rate-distortion function.
result Derives an explicit formula for the sum-rate-distortion function in the special case of identical gradients over edge devices.

We shall introduce the singular curvature function on cuspidal edges of surfaces, which is related to the Gauss-Bonnet formula and which characterizes the shape of cuspidal edges. Moreover, it is closely related to the behavior of the Gaussian curvature of a surface near cuspidal edges and swallowtails.

2005-03-13abs ↗pdf ↗

EDG generates Boltzmann samples from latent variables efficiently.

problem Sampling from complex energy functions in high dimensions.
method Combines variational autoencoders and diffusion models; uses a decoder and diffusion-based encoder.
result EDG outperforms existing methods in various sampling tasks.

EML-CD discovers causal mechanisms from neural networks in a structured way.

problem Extracting causal mechanisms from neural network weights is ill-posed.
method Integrates EML operator into causal structure learning, representing each edge mechanism as a gated EML binary tree.
result Achieves SHD=11.2 +/- 0.4 on real data, matching or outperforming existing methods.

KReTTaH uses tensor trains and Hadamard overparameterization for fast, interpretable multi-way data imputation.

problem Multi-way data imputation for high-dimensional functional MRI and dynamic graph recovery.
method Reformulates imputation as RKHS regression with TT-constrained coefficients and Hadamard overparameterization. Optimizes TT coefficients and kernel matrices on Riemannian manifolds.
result Consistently outperforms state-of-the-art methods in modeling accuracy.

KReTTaH uses tensor trains and Hadamard overparameterization for fast, interpretable multi-way data imputation.

problem Multi-way data imputation in high-dimensional spaces.
method Reformulates imputation as RKHS regression with TT-constrained coefficients, optimized on manifold frameworks.
result Consistently outperforms state-of-the-art methods in accuracy.

GMT improves interpretability of XGNNs by approximating SubMT.

problem Limited understanding of existing interpretable subgraph learning methods.
method Formulated subgraph multilinear extension (SubMT) and designed GMT architecture.
result GMT outperforms state-of-the-art in both interpretability and generalizability.