Selective ensemble-based online adaptive deep neural networks for streaming data with concept drift

H Guo, S Zhang, W Wang - Neural Networks, 2021‏ - Elsevier
Abstract Concept drift is an important issue in the field of streaming data mining. However,
how to maintain real-time model convergence in a dynamic environment is an important and …

Online multi-agent forecasting with interpretable collaborative graph neural networks

M Li, S Chen, Y Shen, G Liu, IW Tsang… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
This article considers predicting future statuses of multiple agents in an online fashion by
exploiting dynamic interactions in the system. We propose a novel collaborative prediction …

On the Necessity of Collaboration for Online Model Selection with Decentralized Data

J Li, Z Wu, Z Xu, I King - Advances in Neural Information …, 2025‏ - proceedings.neurips.cc
We consider online model selection with decentralized data over $ M $ clients, and study the
necessity of collaboration among clients. Previous work proposed various federated …

Concept drift adaptation with continuous kernel learning

Y Chen, HL Dai - Information Sciences, 2024‏ - Elsevier
Abstract Concept drift poses significant challenges in the fields of machine learning and data
mining. At present, many existing algorithms struggle to maintain low error rates or require …

Communication-efficient randomized algorithm for multi-kernel online federated learning

S Hong, J Chae - IEEE transactions on pattern analysis and …, 2021‏ - ieeexplore.ieee.org
Online federated learning (OFL) is a promising framework to learn a sequence of global
functions from distributed sequential data at local devices. In this framework, we first …

Cost-sensitive online adaptive kernel learning for large-scale imbalanced classification

Y Chen, Z Hong, X Yang - IEEE Transactions on Knowledge …, 2023‏ - ieeexplore.ieee.org
Imbalanced classification is a challenging task in the fields of machine learning, data mining
and pattern recognition. Cost-sensitive online algorithms are very important methods for …

Incremental ensemble Gaussian processes

Q Lu, GV Karanikolas… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Belonging to the family of Bayesian nonparametrics, Gaussian process (GP) based
approaches have well-documented merits not only in learning over a rich class of nonlinear …

Ensemble Gaussian processes with spectral features for online interactive learning with scalability

Q Lu, G Karanikolas, Y Shen… - International …, 2020‏ - proceedings.mlr.press
Combining benefits of kernels with Bayesian models, Gaussian process (GP) based
approaches have well-documented merits not only in learning over a rich class of nonlinear …

Nonlinear structural vector autoregressive models with application to directed brain networks

Y Shen, GB Giannakis… - IEEE Transactions on …, 2019‏ - ieeexplore.ieee.org
Structural equation models (SEMs) and vector autoregressive models (VARMs) are two
broad families of approaches that have been shown useful in effective brain connectivity …

Personalized online federated learning with multiple kernels

PM Ghari, Y Shen - Advances in Neural Information …, 2022‏ - proceedings.neurips.cc
Multi-kernel learning (MKL) exhibits well-documented performance in online non-linear
function approximation. Federated learning enables a group of learners (called clients) to …