arXiv research

Paper presents a novel approach for global feature aggregation in Graph Neural Networks.

Quantum computing improves graph neural network aggregation.

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…

Study shows safely discarding features based on aggregate SHAP values is sound.

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…

FedCONST adapts update magnitudes to enhance feature generalization in FL.

Paper tightens statistical aggregation results using local complexity.

Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative…

FABLE incorporates instance features into PWS label models for improved performance.

This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a novel selective attention that deploys a condensation and diffusion mechanism to agg…

Aggregates predictions from multiple regression models using random projections and kernel methods.

ExCIR provides efficient, consistent, and scalable explainability for complex models.

The paper proposes criteria and methods for evaluating and aggregating feature-based model explanations.

FedBE aggregates local models into a robust global model via Bayesian inference.

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 …

GLOBE-CE offers efficient global counterfactual explanations.

Enhances graph neural networks by considering feature similarities in node aggregation.

Estimating global pairwise interaction effects, i.e., the difference between the joint effect and the sum of marginal effects of two input features, with uncertainty properly quantified, is centrally important in science applications. We propose a non-parametric probabilistic method for detecting interaction effects of…

Improved local explainer aggregation for interpretable machine learning models.

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…

A key aspect of Federated Learning (FL) is the requirement of a centralized aggregator to maintain and update the global model. However, in many cases orchestrating a centralized aggregator might be infeasible due to numerous operational constraints. In this paper, we introduce BAFFLE, an aggregator free, blockchain dr…

Study reveals LLM personas have two distinct components: frame-robust aggregated traits and frame-dependent geometric features.

Optimal transport aggregation combines distributed MoE models efficiently.

Unified method for local GBDT feature contributions.

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.

PNA improves GNNs for graph data with multiple aggregators.

Simplifies GNN models by selecting important features for node classification.

FedReLa: A novel data-level approach for imbalanced federated learning

FedLog reduces communication in federated learning by sharing data summaries.

Feature engineering plays an important role in the success of a machine learning model. Most of the effort in training a model goes into data preparation and choosing the right representation. In this paper, we propose a robust feature engineering method, Randomized Union of Locally Linear Subspaces (RULLS). We generat…

We prove a lower bound for feature dimension in linear MDPs and propose a novel dynamics aggregation framework.

Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that the global model may behave abnormally under attacks. To tackle this challenge, …

Federated learning is a distributed, privacy-aware learning scenario which trains a single model on data belonging to several clients. Each client trains a local model on its data and the local models are then aggregated by a central party. Current federated learning methods struggle in cases with heterogeneous client-…

Dynamic defense against Byzantine poisoning in federated learning.

Unified view of GNNs as graph signal denoising.

New method for decentralized learning from diverse clients.

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…

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…

LightSecAgg reduces secure aggregation complexity in FL.

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.

Paper proposes a supervised similarity framework for corporate bonds using RF proximities.

PTOPOFL uses topological descriptors to protect privacy in federated learning.

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…

In many applications, the training data for a machine learning task is partitioned across multiple nodes, and aggregating this data may be infeasible due to communication, privacy, or storage constraints. Existing distributed optimization methods for learning global models in these settings typically aggregate local up…