Mohammad ali vahedifar | Aarhus University (original) (raw)

Uploads

Papers by Mohammad ali vahedifar

Research paper thumbnail of Towards Lifelong Deep Learning: A Review of Continual Learning and Unlearning Methods

Zenodo, 2025

To handle real-world complexities, intelligent systems need to incrementally acquire, update, and... more To handle real-world complexities, intelligent systems need to incrementally acquire, update, and use knowledge throughout their lifetime, a capability known as continual learning (CL). However, neural network training processes face the challenge of catastrophic forgetting (CF), where learning new tasks degrades performance on previously learned ones.
This survey provides a comprehensive overview of CL, including fundamental concepts, theoretical frameworks, methodologies, and practical implementations. Through empirical analysis and benchmarking, it highlights the strengths and weaknesses of state-of-the-art CL methods.
This paper also provides an overview of Machine Unlearning (MU), an emerging paradigm that removes previously learned training data from a trained model, including fundamental concepts, methodologies, and its connections to CL. It also provides a mathematical analysis examining the effect of CF on MU, identifying it as one of the key research directions for facilitating the process of lifelong deep learning in dynamic environments.

Research paper thumbnail of Information Modified K-Nearest Neighbor

arXiv (Cornell University), Dec 3, 2023

The fundamental concept underlying K-Nearest Neighbors (KNN) is the classification of samples bas... more The fundamental concept underlying K-Nearest Neighbors (KNN) is the classification of samples based on the majority through their nearest neighbors. Although distance and neighbors' labels are critical in KNN, traditional KNN treats all samples equally. However, some KNN variants weigh neighbors differently based on a specific rule, considering each neighbor's distance and label. Many KNN methodologies introduce complex algorithms that do not significantly outperform the traditional KNN, often leading to less satisfactory outcomes. The gap in reliably extracting information for accurately predicting true weights remains an open research challenge. In our proposed method, information-modified KNN (IMKNN), we bridge the gap by presenting a straightforward algorithm that achieves effective results. To this end, we introduce a classification method to improve the performance of the KNN algorithm. By exploiting mutual information (MI) and incorporating ideas from Shapley's values, we improve the traditional KNN performance in accuracy, precision, and recall, offering a more refined and effective solution. To evaluate the effectiveness of our method, it is compared with eight variants of KNN. We conduct experiments on 12 widely-used datasets, achieving 11.05%, 12.42%, and 12.07% in accuracy, precision, and recall performance, respectively, compared to traditional KNN. Additionally, we compared IMKNN with traditional KNN across four large-scale datasets to highlight the distinct advantages of IMKNN in the impact of monotonicity, noise, density, subclusters, and skewed distributions. Our research indicates that IMKNN consistently surpasses other methods in diverse datasets.

Research paper thumbnail of Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications

arXiv (Cornell University), Oct 7, 2023

Robust machine learning (ML) models can be developed by leveraging large volumes of data and dist... more Robust machine learning (ML) models can be developed by leveraging large volumes of data and distributing the computational tasks across numerous devices or servers. Federated learning (FL) is a technique in the realm of ML that facilitates this goal by utilizing cloud infrastructure to enable collaborative model training among a network of decentralized devices. Beyond distributing the computational load, FL targets the resolution of privacy issues and the reduction of communication costs simultaneously. To protect user privacy, FL requires users to send model updates rather than transmitting large quantities of raw and potentially confidential data. Specifically, individuals train ML models locally using their own data and then upload the results in the form of weights and gradients to the cloud for aggregation into the global model. This strategy is also advantageous in environments with limited bandwidth or high communication costs, as it prevents the transmission of large data volumes. With the increasing volume of data and rising privacy concerns, alongside the emergence of large-scale ML models like Large Language Models (LLMs), FL presents itself as a timely and relevant solution. It is therefore essential to review current FL algorithms to guide future research that meets the rapidly evolving ML demands. This survey provides a comprehensive analysis and comparison of the most recent FL algorithms, evaluating them on various fronts including mathematical frameworks, privacy protection, resource allocation, and applications. Beyond summarizing existing FL methods, this survey identifies potential gaps, open areas, and future challenges based on the performance reports and algorithms used in recent studies. This survey enables researchers to readily identify existing limitations in the FL field for further exploration.

Research paper thumbnail of Towards Lifelong Deep Learning: A Review of Continual Learning and Unlearning Methods

Zenodo, 2025

To handle real-world complexities, intelligent systems need to incrementally acquire, update, and... more To handle real-world complexities, intelligent systems need to incrementally acquire, update, and use knowledge throughout their lifetime, a capability known as continual learning (CL). However, neural network training processes face the challenge of catastrophic forgetting (CF), where learning new tasks degrades performance on previously learned ones.
This survey provides a comprehensive overview of CL, including fundamental concepts, theoretical frameworks, methodologies, and practical implementations. Through empirical analysis and benchmarking, it highlights the strengths and weaknesses of state-of-the-art CL methods.
This paper also provides an overview of Machine Unlearning (MU), an emerging paradigm that removes previously learned training data from a trained model, including fundamental concepts, methodologies, and its connections to CL. It also provides a mathematical analysis examining the effect of CF on MU, identifying it as one of the key research directions for facilitating the process of lifelong deep learning in dynamic environments.

Research paper thumbnail of Information Modified K-Nearest Neighbor

arXiv (Cornell University), Dec 3, 2023

The fundamental concept underlying K-Nearest Neighbors (KNN) is the classification of samples bas... more The fundamental concept underlying K-Nearest Neighbors (KNN) is the classification of samples based on the majority through their nearest neighbors. Although distance and neighbors' labels are critical in KNN, traditional KNN treats all samples equally. However, some KNN variants weigh neighbors differently based on a specific rule, considering each neighbor's distance and label. Many KNN methodologies introduce complex algorithms that do not significantly outperform the traditional KNN, often leading to less satisfactory outcomes. The gap in reliably extracting information for accurately predicting true weights remains an open research challenge. In our proposed method, information-modified KNN (IMKNN), we bridge the gap by presenting a straightforward algorithm that achieves effective results. To this end, we introduce a classification method to improve the performance of the KNN algorithm. By exploiting mutual information (MI) and incorporating ideas from Shapley's values, we improve the traditional KNN performance in accuracy, precision, and recall, offering a more refined and effective solution. To evaluate the effectiveness of our method, it is compared with eight variants of KNN. We conduct experiments on 12 widely-used datasets, achieving 11.05%, 12.42%, and 12.07% in accuracy, precision, and recall performance, respectively, compared to traditional KNN. Additionally, we compared IMKNN with traditional KNN across four large-scale datasets to highlight the distinct advantages of IMKNN in the impact of monotonicity, noise, density, subclusters, and skewed distributions. Our research indicates that IMKNN consistently surpasses other methods in diverse datasets.

Research paper thumbnail of Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applications

arXiv (Cornell University), Oct 7, 2023

Robust machine learning (ML) models can be developed by leveraging large volumes of data and dist... more Robust machine learning (ML) models can be developed by leveraging large volumes of data and distributing the computational tasks across numerous devices or servers. Federated learning (FL) is a technique in the realm of ML that facilitates this goal by utilizing cloud infrastructure to enable collaborative model training among a network of decentralized devices. Beyond distributing the computational load, FL targets the resolution of privacy issues and the reduction of communication costs simultaneously. To protect user privacy, FL requires users to send model updates rather than transmitting large quantities of raw and potentially confidential data. Specifically, individuals train ML models locally using their own data and then upload the results in the form of weights and gradients to the cloud for aggregation into the global model. This strategy is also advantageous in environments with limited bandwidth or high communication costs, as it prevents the transmission of large data volumes. With the increasing volume of data and rising privacy concerns, alongside the emergence of large-scale ML models like Large Language Models (LLMs), FL presents itself as a timely and relevant solution. It is therefore essential to review current FL algorithms to guide future research that meets the rapidly evolving ML demands. This survey provides a comprehensive analysis and comparison of the most recent FL algorithms, evaluating them on various fronts including mathematical frameworks, privacy protection, resource allocation, and applications. Beyond summarizing existing FL methods, this survey identifies potential gaps, open areas, and future challenges based on the performance reports and algorithms used in recent studies. This survey enables researchers to readily identify existing limitations in the FL field for further exploration.