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.
Aggregates predictions from multiple regression models using random projections and kernel methods.
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.
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…
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.
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.
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.
We prove a lower bound for feature dimension in linear MDPs and propose a novel dynamics aggregation framework.
Unified view of GNNs as graph signal denoising.
The paper develops a method for forecasting power consumption at various levels of aggregation.
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 …
CAggNet improves medical image segmentation by fusing coarse and fine features.
Graph Convolutional Networks (GCNs) have shown very powerful for graph data representation and learning tasks. Existing GCNs usually conduct feature aggregation on a fixed neighborhood graph in which each node computes its representation by aggregating the feature representations of all its neighbors which is biased by…
New method preserves privacy by aggregating feature-vectors with weighted sums, ensuring label differential privacy.
Improves speaker verification for variable-duration utterances using a feature pyramid module.
Quantum computing improves graph neural network aggregation.
SStaGCN improves GCN by stacking and aggregation for better node feature extraction.
regularized logistic regression has now become a workhorse of data mining and bioinformatics: it is widely used for many classification problems, particularly ones with many features. However, regularization typically selects too many features and that so-called false positives are unavoidable. In this pape…
Satellite imagery and remote sensing provide explanatory variables at relatively high resolutions for modeling geospatial phenomena, yet regional summaries are often desirable for analysis and actionable insight. In this paper, we propose a novel method of inducing spatial aggregations as a component of the machine lea…
We present an approach to estimate the severity of traffic related accidents in aggregated (area-level) and disaggregated (point level) data. Exploring spatial features, we measure complexity of road networks using several area level variables. Also using temporal and other situational features from open data for New Y…
Recently, Convolution Neural Networks (CNNs) obtained huge success in numerous vision tasks. In particular, DenseNets have demonstrated that feature reuse via dense skip connections can effectively alleviate the difficulty of training very deep networks and that reusing features generated by the initial layers in all s…
Improved graph neural networks by separating feature aggregation and depth.
FABLE incorporates instance features into PWS label models for improved performance.
A new method for feature selection robust to noise and design variability.
HKConv learns hyperbolic features by aggregating kernel points.
Despite a growing literature on explaining neural networks, no consensus has been reached on how to explain a neural network decision or how to evaluate an explanation. Our contributions in this paper are twofold. First, we investigate schemes to combine explanation methods and reduce model uncertainty to obtain a sing…
We study the problem of detecting adverse drug events in electronic healthcare records. The challenge in this work is to aggregate heterogeneous data types involving diagnosis codes, drug codes, as well as lab measurements. An earlier framework proposed for the same problem demonstrated promising predictive performance…
Optimal transport embedding learns feature sets efficiently.
Simpler GNNs with low-rank non-parametric aggregators perform well on graph benchmarks.
Model reduction of Markov processes is a basic problem in modeling state-transition systems. Motivated by the state aggregation approach rooted in control theory, we study the statistical state compression of a discrete-state Markov chain from empirical trajectories. Through the lens of spectral decomposition, we study…
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…
FedCONST adapts update magnitudes to enhance feature generalization in FL.
Machine learning for healthcare often trains models on de-identified datasets with randomly-shifted calendar dates, ignoring the fact that data were generated under hospital operation practices that change over time. These changing practices induce definitive changes in observed data which confound evaluations which do…
A method to improve clustering explainability using bagging and feature dropout.
Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures. However, insufficient effort has been devoted to the aggregation methods between different convolution graph layers. In this paper, we introduce a graph attribute…
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently. Many successful approaches forgo global approximations in order to provide more faithful local interpretations of the model's behavior. LIME develops multiple interpretable models, each approximat…
Graph smoothing can improve learning performance by restoring lost information.