Zobrazeno 1 - 10
of 120
pro vyhledávání: '"Kuruoglu Ercan Engin"'
In this paper, we propose a novel framework that leverages large language models (LLMs) for predicting missing values in time-varying graph signals by exploiting spatial and temporal smoothness. We leverage the power of LLM to achieve a message-passi
Externí odkaz:
http://arxiv.org/abs/2410.18718
This paper proposes Graph Signal Adaptive Message Passing (GSAMP), a novel message passing method that simultaneously conducts online prediction, missing data imputation, and noise removal on time-varying graph signals. Unlike conventional Graph Sign
Externí odkaz:
http://arxiv.org/abs/2410.17629
The assumption of using a static graph to represent multivariate time-varying signals oversimplifies the complexity of modeling their interactions over time. We propose a Dynamic Multi-hop model that captures dynamic interactions among time-varying n
Externí odkaz:
http://arxiv.org/abs/2410.17625
Autism Spectrum Disorder (ASD) is a prevalent neurological disorder. However, the multi-faceted symptoms and large individual differences among ASD patients are hindering the diagnosis process, which largely relies on subject descriptions and lacks q
Externí odkaz:
http://arxiv.org/abs/2410.16874
Designing network parameters that can effectively represent complex networks is of significant importance for the analysis of time-varying complex networks. This paper introduces a novel thermodynamic framework for analyzing complex networks, focusin
Externí odkaz:
http://arxiv.org/abs/2409.01039
We introduce for continual learning Autodiff Quadratic Consolidation (AQC), which approximates the previous loss function with a quadratic function, and Neural Consolidation (NC), which approximates the previous loss function with a neural network. A
Externí odkaz:
http://arxiv.org/abs/2405.16498
Autor:
Luo, Mengen, Kuruoglu, Ercan Engin
Federated learning's poor performance in the presence of heterogeneous data remains one of the most pressing issues in the field. Personalized federated learning departs from the conventional paradigm in which all clients employ the same model, inste
Externí odkaz:
http://arxiv.org/abs/2402.16091
Performance degradation owing to data heterogeneity and low output interpretability are the most significant challenges faced by federated learning in practical applications. Personalized federated learning diverges from traditional approaches, as it
Externí odkaz:
http://arxiv.org/abs/2402.16911
The online prediction of multivariate signals, existing simultaneously in space and time, from noisy partial observations is a fundamental task in numerous applications. We propose an efficient Neural Network architecture for the online estimation of
Externí odkaz:
http://arxiv.org/abs/2401.15304
Autor:
Hong, Junping, Kuruoglu, Ercan Engin
This paper is a preliminary study of the robustness and noise analysis of deep neural networks via a game theory formulation Bayesian Neural Networks (BNN) and the maximal coding rate distortion loss. BNN has been shown to provide some robustness to
Externí odkaz:
http://arxiv.org/abs/2311.11126