arXiv research

Study improves forecasting of aggregated curves in electricity markets.

SCHA-VAE generates novel data from limited examples using hierarchical context aggregation.

Data aggregation improves HAC for resource-constrained systems.

HierarchicalForecast provides a Python framework for coherent hierarchical forecasting.

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

A simple guide to understanding hierarchical causality in complex systems.

This study addresses the issue of predicting the glaucomatous visual field loss from patient disease datasets. Our goal is to accurately predict the progress of the disease in individual patients. As very few measurements are available for each patient, it is difficult to produce good predictors for individuals. A rece…

Federated Learning speeds up speech recognition training by 7x and reduces error rate by 6%.

Unsupervised method learns hierarchical graph representations without labels.

Graph Neural Networks (GNNs) are based on repeated aggregations of information across nodes' neighbors in a graph. However, because common neighbors are shared between different nodes, this leads to repeated and inefficient computations. We propose Hierarchically Aggregated computation Graphs (HAGs), a new GNN graph re…

This paper addresses privacy in federated learning with wireless clients and base stations.

The ability to adequately model risks is crucial for insurance companies. The method of "Copula-based hierarchical risk aggregation" by Arbenz et al. offers a flexible way in doing so and has attracted much attention recently. We briefly introduce the aggregation tree model as well as the sampling algorithm proposed by…

A new hierarchical clustering method selects representative points from sub-minimum-spanning-trees.

The paper develops a method for forecasting power consumption at various levels of aggregation.

Enhances neural forecasting for hierarchically organized time series data.

The benefits of diversifying risks are difficult to estimate quantitatively because of the uncertainties in the dependence structure between the risks. Also, the modelling of multidimensional dependencies is a non-trivial task. This paper focuses on one such technique for portfolio aggregation, namely the aggregation o…

New method explains ML performance gaps without causal knowledge.

Hierarchical Partial-Order Models for Ranking

VFG model embeds flow-based models with hierarchical structures using variational inference.

We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets. Exploiting tools from Bayesian nonparametrics, we develop a general meta-modeling framework that learns shared global latent structures by identifying correspondences among local model parameterizations. Our propose…

Hierarchical framework for model evaluation on leaderboards

Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism, which prevents the model from obtaining adequate global information. In order to …

A new hierarchical forecasting method using machine learning improves forecast accuracy.

We introduce a novel algorithm of community detection that maintains dynamically a community structure of a large network that evolves with time. The algorithm maximizes the modularity index thanks to the construction of a randomized hierarchical clustering based on a Monte Carlo Markov Chain (MCMC) method. Interesting…

This paper solves aggregation of Pareto optimal models by using Bayesian priors and weighted averaging.

Study identifies contagion in aggregated defaults despite environmental changes.

Using powerful posterior distributions is a popular approach to achieving better variational inference. However, recent works showed that the aggregated posterior may fail to match unit Gaussian prior, thus learning the prior becomes an alternative way to improve the lower-bound. In this paper, for the first time in th…

CoRe method improves time series forecasting coherency without strict constraints.

Improved sales forecasting at various levels using ensemble methods.

Proposes HOTA-FedGradNorm for faster and robust PFL in noisy channels.

This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction. Specifically, we combine state aggregation with the options framework and demonstrate that they work well together and indeed it is only after one combines the two that the full benefit of each is re…

Representation learning is an essential problem in a wide range of applications and it is important for performing downstream tasks successfully. In this paper, we propose a new model that learns coupled representations of domains, intents, and slots by taking advantage of their hierarchical dependency in a Spoken Lang…

Paper uses HGNN to predict stock types from relationships and temporal data.

HEBAE improves VAEs by adaptively balancing reconstruction and regularization.

The paper quantifies uncertainty in aggregated machine learning metrics.

A novel framework combines LLMs and RL for financial portfolio optimization.

We present a comparative study of different probabilistic forecasting techniques on the task of predicting the electrical load of secondary substations and cabinets located in a low voltage distribution grid, as well as their aggregated power profile. The methods are evaluated using standard KPIs for deterministic and …

Traditional non-life reserving models largely neglect the vast amount of information collected over the lifetime of a claim. This information includes covariates describing the policy, claim cause as well as the detailed history collected during a claim's development over time. We present the hierarchical reserving mod…

We introduce HTAD, a novel model for diagnosis prediction using Electronic Health Records (EHR) represented as Heterogeneous Information Networks. Recent studies on modeling EHR have shown success in automatically learning representations of the clinical records in order to avoid the need for manual feature selection. …

New methods improve electricity load forecasting using hierarchical transfer learning.

Study compares local and global models for hierarchical forecasting accuracy.

Paper proposes a new method for predicting DER adoption with hierarchical guarantees.

Policy-GNN optimizes GNN aggregation for diverse node iterations.

To improve the resilience of distributed training to worst-case, or Byzantine node failures, several recent approaches have replaced gradient averaging with robust aggregation methods. Such techniques can have high computational costs, often quadratic in the number of compute nodes, and only have limited robustness gua…

We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we…

Study identifies key ESG variables for assessing financial risk.

We study clustering methods for binary data, first defining aggregation criteria that measure the compactness of clusters. Five new and original methods are introduced, using neighborhoods and population behavior combinatorial optimization metaheuristics: first ones are simulated annealing, threshold accepting and tabu…

A new multi-phase approach improves supply chain forecasting accuracy.