Author name cluster

Junhua Zhao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

AAAI Conference 2025 Conference Paper

Federated Unlearning with Gradient Descent and Conflict Mitigation

Zibin Pan
Zhichao Wang
Chi Li
Kaiyan Zheng
Boqi Wang
Xiaoying Tang
Junhua Zhao

Federated Learning (FL) has received much attention in recent years. However, although clients are not required to share their data in FL, the global model itself can implicitly remember clients' local data. Therefore, it’s necessary to effectively remove the target client's data from the FL global model to ease the risk of privacy leakage and implement "the right to be forgotten". Federated Unlearning (FU) has been considered a promising solution to remove data without full retraining. But the model utility easily suffers significant reduction during unlearning due to the gradient conflicts. Furthermore, when conducting the post-training to recovery the model utility, it’s prone to move back and revert what have already been unlearned. To address these issues, we propose Federated Unlearning with Orthogonal Steepest Descent (FedOSD). We first design an unlearning cross entropy loss to overcome the convergence issue of the gradient ascent. A steepest descent direction for unlearning is then calculated in the condition of being non-conflicting with other clients’ gradients and closest to the target client's gradient. This benefits to efficiently unlearn and mitigate the model utility reduction. After unlearning, we recover the model utility by maintaining the achievement of unlearning. Finally, extensive experiments in several FL scenarios verify that FedOSD outperforms the SOTA FU algorithms in terms of unlearning and the model utility.

PDF Details DOI

AAAI Conference 2024 Conference Paper

FedLF: Layer-Wise Fair Federated Learning

Zibin Pan
Chi Li
Fangchen Yu
Shuyi Wang
Haijin Wang
Xiaoying Tang
Junhua Zhao

Fairness has become an important concern in Federated Learning (FL). An unfair model that performs well for some clients while performing poorly for others can reduce the willingness of clients to participate. In this work, we identify a direct cause of unfairness in FL - the use of an unfair direction to update the global model, which favors some clients while conflicting with other clients’ gradients at the model and layer levels. To address these issues, we propose a layer-wise fair Federated Learning algorithm (FedLF). Firstly, we formulate a multi-objective optimization problem with an effective fair-driven objective for FL. A layer-wise fair direction is then calculated to mitigate the model and layer-level gradient conflicts and reduce the improvement bias. We further provide the theoretical analysis on how FedLF can improve fairness and guarantee convergence. Extensive experiments on different learning tasks and models demonstrate that FedLF outperforms the SOTA FL algorithms in terms of accuracy and fairness. The source code is available at https://github.com/zibinpan/FedLF.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection

Xinlei Wang
Maike Feng
Jing Qiu
Jinjin Gu
Junhua Zhao

This paper introduces a novel approach that leverages Large Language Models (LLMs) and Generative Agents to enhance time series forecasting by reasoning across both text and time series data. With language as a medium, our method adaptively integrates social events into forecasting models, aligning news content with time series fluctuations to provide richer insights. Specifically, we utilize LLM-based agents to iteratively filter out irrelevant news and employ human-like reasoning to evaluate predictions. This enables the model to analyze complex events, such as unexpected incidents and shifts in social behavior, and continuously refine the selection logic of news and the robustness of the agent's output. By integrating selected news events with time series data, we fine-tune a pre-trained LLM to predict sequences of digits in time series. The results demonstrate significant improvements in forecasting accuracy, suggesting a potential paradigm shift in time series forecasting through the effective utilization of unstructured news data.

PDF Details DOI

EAAI Journal 2024 Journal Article

Real-time industrial carbon emission estimation with deep learning-based device recognition and incomplete smart meter data

Jinjie Liu
Guolong Liu
Huan Zhao
Junhua Zhao
Jing Qiu
Zhao Yang Dong

Real-time industrial carbon emission estimation aims to estimate emissions more accurately to promote carbon reduction and mitigate climate change. Compared with input-output-based (IOA) analysis methods, the process-based analysis (PA) methods provide more specific information to decision-makers based on extensive detailed data. However, the required data is hard to obtain and normally contains missing data. To address these challenges, this paper proposes a novel deep learning-based carbon emission estimation framework to track the emissions of industrial customers in smart grids with smart meter data. The proposed framework encompasses three pivotal stages: data imputation, device recognition, and emission estimation—collectively referred to as DI-DR-EE. Specifically, the Data Imputation Network (DINet) based on super-resolution perception (SRP) is first introduced to recover the missing smart meter data. Then the recovered data is used to recognize the device states through the Device Recognition Network (DRNet), which thrives upon subspace blueprint separable convolutions (BSConv-S) to elevate the accuracy of device recognition with low-frequency data, all the while optimizing computational efficiency. Finally, the direct emission estimation is conducted based on the device states, and the indirect emission is estimated based on the power consumption. Case studies with five factories connected to the IEEE 57-bus system have verified the effectiveness of the proposed framework. The model training process was executed using Python with PyTorch version 1. 8. 1, coupled with Cuda 11. 1 for accelerated computations. Results underscore that DINet and DRNet outperform established benchmarks, while DI-DR-EE remarkably maintains its capacity to attain estimations within a 10% margin of error, even when grappling with up to 90% missing meter data.

Details DOI

EAAI Journal 2024 Journal Article

Resilient dynamic microgrid formation by deep reinforcement learning integrating physics-informed neural networks

Mingze Xu
Shunbo Lei
Chong Wang
Liang Liang
Junhua Zhao
Chaoyi Peng

Dynamic microgrid formation can enhance topological flexibility within the distribution system, particularly during extreme events, thereby facilitating a more efficient restoration process. However, existing research has overlooked the impact of cold load pickup on system restoration efforts. A sudden load spike can lead to the overloading of generators and transformers, which can result in the failure of the system restoration process. This study leverages the topological flexibility through dynamic microgrid formation of the system to mitigate the impact of cold load pickup, thereby enhancing the efficiency of sequential load restoration. To alleviate the computational complexity arising from intricate operational constraints and the uncertainties inherent in cold load pickup conditions, this paper proposes a novel model-free framework. Unlike existing deep reinforcement learning models, we incorporate physical constraint information into the model by means of physics-informed neural networks, where the solution of an optimization problem is regarded as knowledge, enabling the agent to learn operational constraints more efficiently and stably. The proposed approach is compatible with and can be integrated into any deep reinforcement learning algorithm that utilizes the advantage actor–critic framework with neural networks. This research employs the deep deterministic policy gradient algorithm as a representative example for investigation. The effectiveness and generalization performance of the proposed method are validated on a modified IEEE 123-node test feeder, while its scalability is assessed using the IEEE 8500-node test feeder system.

Details DOI

AAAI Conference 2023 Conference Paper

FedMDFG: Federated Learning with Multi-Gradient Descent and Fair Guidance

Zibin Pan
Shuyi Wang
Chi Li
Haijin Wang
Xiaoying Tang
Junhua Zhao

Fairness has been considered as a critical problem in federated learning (FL). In this work, we analyze two direct causes of unfairness in FL - an unfair direction and an improper step size when updating the model. To solve these issues, we introduce an effective way to measure fairness of the model through the cosine similarity, and then propose a federated multiple gradient descent algorithm with fair guidance (FedMDFG) to drive the model fairer. We first convert FL into a multi-objective optimization problem (MOP) and design an advanced multiple gradient descent algorithm to calculate a fair descent direction by adding a fair-driven objective to MOP. A low-communication-cost line search strategy is then designed to find a better step size for the model update. We further show the theoretical analysis on how it can enhance fairness and guarantee the convergence. Finally, extensive experiments in several FL scenarios verify that FedMDFG is robust and outperforms the SOTA FL algorithms in convergence and fairness. The source code is available at https://github.com/zibinpan/FedMDFG.

PDF Details DOI