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.
Paper presents a novel approach for global feature aggregation in Graph Neural Networks.
Non-local GNNs improve performance on disassortative graphs.
Deep learning has shown its great promise in various biomedical image segmentation tasks. Existing models are typically based on U-Net and rely on an encoder-decoder architecture with stacked local operators to aggregate long-range information gradually. However, only using the local operators limits the efficiency and…
This paper improves image super-resolution by integrating cross-scale non-local attention.
Road extraction from very high resolution satellite (VHR) images is one of the most important topics in the field of remote sensing. In this paper, we propose an efficient Non-Local LinkNet with non-local blocks that can grasp relations between global features. This enables each spatial feature point to refer to all ot…
Purpose: Lung nodules have very diverse shapes and sizes, which makes classifying them as benign/malignant a challenging problem. In this paper, we propose a novel method to predict the malignancy of nodules that have the capability to analyze the shape and size of a nodule using a global feature extractor, as well as …
Deep learning model predicts traffic flows across entire network for multiple steps ahead.
Softmax is found ineffective for NL block, leading to improved performance.
Multiple sclerosis (MS) is an inflammatory demyelinating disease of the central nervous system (CNS) that results in focal injury to the grey and white matter. The presence of white matter lesions biases morphometric analyses such as registration, individual longitudinal measurements and tissue segmentation for brain v…
We introduce a notion of non-local almost minimal boundaries similar to that introduced by Almgren in geometric measure theory. Extending methods developed recently for non-local minimal surfaces we prove that flat non-local almost minimal boundaries are smooth. This can be viewed as a non-local version of the Almgren-…
Aggregates predictions from multiple regression models using random projections and kernel methods.
3D Axial-Attention improves lung nodule classification accuracy.
The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.
In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate …
Enhances graph neural networks by considering feature similarities in node aggregation.
It is argued that the enlargement of the gauge group found in non-commutative gauge theory is more fundamentally thought of as a consequence of the non-locality of the construction and that it was already encountered in an earlier discussion of a non-local gauge theory.
Proposes a novel MTL approach based on bias-variance analysis.
This paper introduces a family of local feature aggregation functions and a novel method to estimate their parameters, such that they generate optimal representations for classification (or any task that can be expressed as a cost function minimization problem). To achieve that, we compose the local feature aggregation…
In this paper, we study two kind of L^2 norm preserved non-local heat flows on closed manifolds. We first study the global existence, stability and asymptotic behavior to such non-local heat flows. Next we give the gradient estimates of positive solutions to these heat flows.
Fractional porous media equations yield q-Gaussian solutions for stock price returns.
Study shows safely discarding features based on aggregate SHAP values is sound.
Study reveals LLM personas have two distinct components: frame-robust aggregated traits and frame-dependent geometric features.
The ability to witness non-local correlations lies at the core of foundational aspects of quantum mechanics and its application in the processing of information. Commonly, this is achieved via the violation of Bell inequalities. Unfortunately, however, their systematic derivation quickly becomes unfeasible as the scena…
We study bi-Hamiltonian systems of hydrodynamic type with non-singular (semisimple) non-local bi-Hamiltonian structures and prove that such systems of hydrodynamic type are diagonalizable. Moreover, we prove that for an arbitrary non-singular (semisimple) non-locally bi-Hamiltonian system of hydrodynamic type, there ex…
Graph convolutional network (GCN) is an emerging neural network approach. It learns new representation of a node by aggregating feature vectors of all neighbors in the aggregation process without considering whether the neighbors or features are useful or not. Recent methods have improved solutions by sampling a fixed …
Two new algorithms reduce feature space while preserving non-linear relationships.
Improved disentanglement in VAEs using aggregated feature maps.
In this paper, we study CAT(0) spaces with non-locally connected boundary. We give some condition of a CAT(0) space whose boundary is not locally connected.
In this paper, we study global existence and blow up properties to norm preserving non-local heat flows. We first study two kinds of norm preserving non-local flows and prove that these flows have the global solutions. Finally, we give a example to show that one kind of this heat flow may blow up in $L^{\in…
PNA improves GNNs for graph data with multiple aggregators.
Simplifies GNN models by selecting important features for node classification.
Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances to describe how much influence a training point exerts on a test point, while the latter attempts to attribute value to the features most pe…
Improved disentanglement through learned feature aggregation.
MFNs parameterize non-local interactions through matrix equivariant functions, improving graph neural network performance.
We prove a lower bound for feature dimension in linear MDPs and propose a novel dynamics aggregation framework.
Complex textual information extraction tasks are often posed as sequence labeling or \emph{shallow parsing}, where fields are extracted using local labels made consistent through probabilistic inference in a graphical model with constrained transitions. Recently, it has become common to locally parametrize these models…
Weather2vec learns representations to adjust for non-local confounding in air pollution studies.
Finite volume ends found in quaternionic Kähler manifolds.
Study non-local isoperimetric energies on spheres using a Riemannian autocorrelation function.
Gradients help find global optima in complex functions.
Backward stochastic partial differential equations of parabolic type in bounded domains are studied in the setting where the coercivity condition is not necessary satisfied and the equation can be degenerate. Some generalized solutions based on the representation theorem are suggested. In addition to problems with a st…
Unified view of GNNs as graph signal denoising.
The paper develops a method for forecasting power consumption at various levels of aggregation.
Scientific discovery is limited by hypothesis redundancy, and hybrid methods can exploit non-local exploration.
In this paper, we consider a kind of area preserving non-local flow for convex curves in the plane. We show that the flow exists globally, the length of evolving curve is non-increasing, and the curve converges to a circle in C^{\infty} sense as time goes into infinity.
Learning the true ordering between objects by aggregating a set of expert opinion rank order lists is an important and ubiquitous problem in many applications ranging from social choice theory to natural language processing and search aggregation. We study the problem of unsupervised rank aggregation where no ground tr…
Approach for modeling EHR data with rare features, improving prediction and interpretation.
Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also …