Abdullah Alchihabi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Abdullah Alchihabi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Yuhong Guo
Carleton University
4 shared publications - Adnan Yazici
Nazarbayev University
1 shared publication - Arash Rahnama
Department of Electrical Engineering, University of Notre Dame, Notre Dame, IN United States of America 46556
1 shared publication Baran B. Kivilcim
Department of Computer Engineering, Middle East Technical University, Ankara, Turkey
1 shared publicationFatos T. Yarman Vural
Department of Computer Engineering, Middle East Technical University, Ankara, Turkey
1 shared publication- Fatos T. Yarman Vural
Department of Computer Engineering, Middle East Technical University, Ankara, Turkey
1 shared publication
Latest Publications
- Open Access
Unbiased GNN Learning via Fairness-Aware Subgraph Diffusion
Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in tackling a wide array of graph-related tasks across diverse domains. However, a significant challenge lies in their propensity to generate biased predictions, particularly with respect to sensitive node attributes such as age and gender. These biases, inherent in many machine learning models, are amplified in GNNs due to the message-passing mechanism, which allows nodes to influence each other, rendering the task of making fair predictions notably challenging. This issue is particularly pertinent in critical domains where model fairness holds paramount importance. In this paper, we propose a novel generative Fairness-Aware Subgraph Diffusion (FASD) method for unbiased GNN learning. The method initiates by strategically sampling small subgraphs from the original large input graph, and then proceeds to conduct subgraph debiasing via generative fairness-aware graph diffusion processes based on stochastic differential equations (SDEs). To effectively diffuse unfairness in the input data, we introduce additional adversary bias perturbations to the subgraphs during the forward diffusion process, and train score-based models to predict these applied perturbations, enabling them to learn the underlying dynamics of the biases present in the data. Subsequently, the trained score-based models are utilized to further debias the original subgraph samples through the reverse diffusion process. Finally, FASD induces fair node predictions on the input graph by performing standard GNN learning on the debiased subgraphs. Experimental results demonstrate the superior performance of the proposed method over state-of-the-art Fair GNN baselines across multiple benchmark datasets.
Open AccessUnbiased GNN Learning via Fairness-Aware Subgraph Diffusion
Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in tackling a wide array of graph-related tasks across diverse domains. However, a significant challenge lies in their propensity to generate biased predictions, particularly with respect to sensitive node attributes such as age and gender. These biases, inherent in many machine learning models, are amplified in GNNs due to the message-passing mechanism, which allows nodes to influence each other, rendering the task of making fair predictions notably challenging. This issue is particularly pertinent in critical domains where model fairness holds paramount importance. In this paper, we propose a novel generative Fairness-Aware Subgraph Diffusion (FASD) method for unbiased GNN learning. The method initiates by strategically sampling small subgraphs from the original large input graph, and then proceeds to conduct subgraph debiasing via generative fairness-aware graph diffusion processes based on stochastic differential equations (SDEs). To effectively diffuse unfairness in the input data, we introduce additional adversary bias perturbations to the subgraphs during the forward diffusion process, and train score-based models to predict these applied perturbations, enabling them to learn the underlying dynamics of the biases present in the data. Subsequently, the trained score-based models are utilized to further debias the original subgraph samples through the reverse diffusion process. Finally, FASD induces fair node predictions on the input graph by performing standard GNN learning on the debiased subgraphs. Experimental results demonstrate the superior performance of the proposed method over state-of-the-art Fair GNN baselines across multiple benchmark datasets.
- Open Access
Efficient Low-Rank GNN Defense Against Structural Attacks
Graph Neural Networks (GNNs) have been shown to possess strong representation abilities over graph data. However, GNNs are vulnerable to adversarial attacks, and even minor perturbations to the graph structure can significantly degrade their performance. Existing methods either are ineffective against sophisticated attacks or require the optimization of dense adjacency matrices, which is time-consuming and prone to local minima. To remedy this problem, we propose an Efficient Low-Rank Graph Neural Network (ELR-GNN) defense method, which aims to learn low-rank and sparse graph structures for defending against adversarial attacks, ensuring effective defense with greater efficiency. Specifically, ELR-GNN consists of two modules: a Coarse Low-Rank Estimation Module and a Fine-Grained Estimation Module. The first module adopts the truncated Singular Value Decomposition (SVD) to initialize the low-rank adjacency matrix estimation, which serves as a starting point for optimizing the low-rank matrix. In the second module, the initial estimate is refined by jointly learning a low-rank sparse graph structure with the GNN model. Sparsity is incorporated into the learned low-rank adjacency matrix by pruning weak connections, which can reduce redundant data while maintaining valuable information. As a result, instead of using the dense adjacency matrix directly, ELR-GNN can learn a low-rank and sparse estimate of it in a simple, efficient and easy to optimize manner. The experimental results demonstrate that ELR-GNN outperforms the state-of-the-art GNN defense methods in the literature, in addition to being very efficient and easy to train.
Open AccessEfficient Low-Rank GNN Defense Against Structural Attacks
Graph Neural Networks (GNNs) have been shown to possess strong representation abilities over graph data. However, GNNs are vulnerable to adversarial attacks, and even minor perturbations to the graph structure can significantly degrade their performance. Existing methods either are ineffective against sophisticated attacks or require the optimization of dense adjacency matrices, which is time-consuming and prone to local minima. To remedy this problem, we propose an Efficient Low-Rank Graph Neural Network (ELR-GNN) defense method, which aims to learn low-rank and sparse graph structures for defending against adversarial attacks, ensuring effective defense with greater efficiency. Specifically, ELR-GNN consists of two modules: a Coarse Low-Rank Estimation Module and a Fine-Grained Estimation Module. The first module adopts the truncated Singular Value Decomposition (SVD) to initialize the low-rank adjacency matrix estimation, which serves as a starting point for optimizing the low-rank matrix. In the second module, the initial estimate is refined by jointly learning a low-rank sparse graph structure with the GNN model. Sparsity is incorporated into the learned low-rank adjacency matrix by pruning weak connections, which can reduce redundant data while maintaining valuable information. As a result, instead of using the dense adjacency matrix directly, ELR-GNN can learn a low-rank and sparse estimate of it in a simple, efficient and easy to optimize manner. The experimental results demonstrate that ELR-GNN outperforms the state-of-the-art GNN defense methods in the literature, in addition to being very efficient and easy to train.
- Open Access
GDM: Dual Mixup for Graph Classification with Limited Supervision
Graph Neural Networks (GNNs) require a large number of labeled graph samples to obtain good performance on the graph classification task. The performance of GNNs degrades significantly as the number of labeled graph samples decreases. To reduce the annotation cost, it is therefore important to develop graph augmentation methods that can generate new graph instances to increase the size and diversity of the limited set of available labeled graph samples. In this work, we propose a novel mixup-based graph augmentation method, Graph Dual Mixup (GDM), that leverages both functional and structural information of the graph instances to generate new labeled graph samples. GDM employs a graph structural auto-encoder to learn structural embeddings of the graph samples, and then applies mixup to the structural information of the graphs in the learned structural embedding space and generates new graph structures from the mixup structural embeddings. As for the functional information, GDM applies mixup directly to the input node features of the graph samples to generate functional node feature information for new mixup graph instances. Jointly, the generated input node features and graph structures yield new graph samples which can supplement the set of original labeled graphs. Furthermore, we propose two novel Balanced Graph Sampling methods to enhance the balanced difficulty and diversity for the generated graph samples. Experimental results on the benchmark datasets demonstrate that our proposed method substantially outperforms the state-of-the-art graph augmentation methods when the labeled graphs are scarce.
Open AccessGDM: Dual Mixup for Graph Classification with Limited Supervision
Graph Neural Networks (GNNs) require a large number of labeled graph samples to obtain good performance on the graph classification task. The performance of GNNs degrades significantly as the number of labeled graph samples decreases. To reduce the annotation cost, it is therefore important to develop graph augmentation methods that can generate new graph instances to increase the size and diversity of the limited set of available labeled graph samples. In this work, we propose a novel mixup-based graph augmentation method, Graph Dual Mixup (GDM), that leverages both functional and structural information of the graph instances to generate new labeled graph samples. GDM employs a graph structural auto-encoder to learn structural embeddings of the graph samples, and then applies mixup to the structural information of the graphs in the learned structural embedding space and generates new graph structures from the mixup structural embeddings. As for the functional information, GDM applies mixup directly to the input node features of the graph samples to generate functional node feature information for new mixup graph instances. Jointly, the generated input node features and graph structures yield new graph samples which can supplement the set of original labeled graphs. Furthermore, we propose two novel Balanced Graph Sampling methods to enhance the balanced difficulty and diversity for the generated graph samples. Experimental results on the benchmark datasets demonstrate that our proposed method substantially outperforms the state-of-the-art graph augmentation methods when the labeled graphs are scarce.
- 17 September 2023
- Published by Springer Nature
- p. 309-324
GDM: Dual Mixup for Graph Classification with Limited Supervision
- 17 September 2023
- Published by Springer Nature
- p. 309-324
GDM: Dual Mixup for Graph Classification with Limited Supervision
- Open Access
- 10 December 2021
- Published by Frontiers Media SA in Frontiers in Neuroinformatics
- Vol. 15, 670052
Analyzing Complex Problem Solving by Dynamic Brain Networks
Complex problem solving is a high level cognitive task of the human brain, which has been studied over the last decade. Tower of London (TOL) is a game that has been widely used to study complex problem solving. In this paper, we aim to explore the underlying cognitive network structure among anatomical regions of complex problem solving and its subtasks, namely planning and execution. A new computational model for estimating a brain network at each time instant of fMRI recordings is proposed. The suggested method models the brain network as an Artificial Neural Network, where the weights correspond to the relationships among the brain anatomic regions. The first step of the model is preprocessing that manages to decrease the spatial redundancy while increasing the temporal resolution of the fMRI recordings. Then, dynamic brain networks are estimated using the preprocessed fMRI signal to train the Artificial Neural Network. The properties of the estimated brain networks are studied in order to identify regions of interest, such as hubs and subgroups of densely connected brain regions. The representation power of the suggested brain network is shown by decoding the planning and execution subtasks of complex problem solving. Our findings are consistent with the previous results of experimental psychology. Furthermore, it is observed that there are more hubs during the planning phase compared to the execution phase, and the clusters are more strongly connected during planning compared to execution.
- 10 December 2021
- Published by Frontiers Media SA in Frontiers in Neuroinformatics
- Vol. 15, 670052
Open AccessAnalyzing Complex Problem Solving by Dynamic Brain Networks
Complex problem solving is a high level cognitive task of the human brain, which has been studied over the last decade. Tower of London (TOL) is a game that has been widely used to study complex problem solving. In this paper, we aim to explore the underlying cognitive network structure among anatomical regions of complex problem solving and its subtasks, namely planning and execution. A new computational model for estimating a brain network at each time instant of fMRI recordings is proposed. The suggested method models the brain network as an Artificial Neural Network, where the weights correspond to the relationships among the brain anatomic regions. The first step of the model is preprocessing that manages to decrease the spatial redundancy while increasing the temporal resolution of the fMRI recordings. Then, dynamic brain networks are estimated using the preprocessed fMRI signal to train the Artificial Neural Network. The properties of the estimated brain networks are studied in order to identify regions of interest, such as hubs and subgroups of densely connected brain regions. The representation power of the suggested brain network is shown by decoding the planning and execution subtasks of complex problem solving. Our findings are consistent with the previous results of experimental psychology. Furthermore, it is observed that there are more hubs during the planning phase compared to the execution phase, and the clusters are more strongly connected during planning compared to execution.
- 28 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 26 (6) , 3615-3629
A Two-Tier Distributed Fuzzy Logic Based Protocol for Efficient Data Aggregation in Multihop Wireless Sensor Networks
This study proposes a two-tier distributed fuzzy logic based protocol in order to improve efficiency of data aggregation operations in multi-hop wireless sensor networks (WSNs). Clustering is utilized for efficient aggregation requirements in terms of consumed energy. In a clustered network, member (leaf) nodes transmit obtained data to cluster-heads (CH) and CHs relay received packets to the base station. In multi-hop wireless networks, this CH-generated transmission occurs over other CHs. Due to the adoption of a multi-hop topology, hotspots and/or energy-hole problems may arise. In this paper, we propose a Two-Tier Distributed Fuzzy Logic Based Protocol (TTDFP) to extend the lifespan of multi-hop WSNs by taking the efficiency of clustering and routing phases jointly into account. The proposed protocol, TTDFP, is a distribution-adaptive protocol that runs and scales efficiently for sensor network applications. Additionally, along with the two-tier fuzzy logic based protocol, we utilize an optimization framework to tune the parameters used in the fuzzy clustering tier in order to optimize the performance of a given WSN. This paper also includes performance comparisons and experimental evaluations with the selected state-of-the-art algorithms. The experimental results reveal that TTDFP performs better than any of the other protocols under the same network setup considering metrics used for comparing energy-efficiency and network lifespan of the protocols.
- 28 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 26 (6) , 3615-3629
A Two-Tier Distributed Fuzzy Logic Based Protocol for Efficient Data Aggregation in Multihop Wireless Sensor Networks
This study proposes a two-tier distributed fuzzy logic based protocol in order to improve efficiency of data aggregation operations in multi-hop wireless sensor networks (WSNs). Clustering is utilized for efficient aggregation requirements in terms of consumed energy. In a clustered network, member (leaf) nodes transmit obtained data to cluster-heads (CH) and CHs relay received packets to the base station. In multi-hop wireless networks, this CH-generated transmission occurs over other CHs. Due to the adoption of a multi-hop topology, hotspots and/or energy-hole problems may arise. In this paper, we propose a Two-Tier Distributed Fuzzy Logic Based Protocol (TTDFP) to extend the lifespan of multi-hop WSNs by taking the efficiency of clustering and routing phases jointly into account. The proposed protocol, TTDFP, is a distribution-adaptive protocol that runs and scales efficiently for sensor network applications. Additionally, along with the two-tier fuzzy logic based protocol, we utilize an optimization framework to tune the parameters used in the fuzzy clustering tier in order to optimize the performance of a given WSN. This paper also includes performance comparisons and experimental evaluations with the selected state-of-the-art algorithms. The experimental results reveal that TTDFP performs better than any of the other protocols under the same network setup considering metrics used for comparing energy-efficiency and network lifespan of the protocols.
- Open Access
Encoding Multi-Resolution Brain Networks Using Unsupervised Deep Learning
The main goal of this study is to extract a set of brain networks in multiple time-resolutions to analyze the connectivity patterns among the anatomic regions for a given cognitive task. We suggest a deep architecture which learns the natural groupings of the connectivity patterns of human brain in multiple time-resolutions. The suggested architecture is tested on task data set of Human Connectome Project (HCP) where we extract multi-resolution networks, each of which corresponds to a cognitive task. At the first level of this architecture, we decompose the fMRI signal into multiple sub-bands using wavelet decompositions. At the second level, for each sub-band, we estimate a brain network extracted from short time windows of the fMRI signal. At the third level, we feed the adjacency matrices of each mesh network at each time-resolution into an unsupervised deep learning algorithm, namely, a Stacked De- noising Auto-Encoder (SDAE). The outputs of the SDAE provide a compact connectivity representation for each time window at each sub-band of the fMRI signal. We concatenate the learned representations of all sub-bands at each window and cluster them by a hierarchical algorithm to find the natural groupings among the windows. We observe that each cluster represents a cognitive task with a performance of 93% Rand Index and 71% Adjusted Rand Index. We visualize the mean values and the precisions of the networks at each component of the cluster mixture. The mean brain networks at cluster centers show the variations among cognitive tasks and the precision of each cluster shows the within cluster variability of networks, across the subjects.
Open AccessEncoding Multi-Resolution Brain Networks Using Unsupervised Deep Learning
The main goal of this study is to extract a set of brain networks in multiple time-resolutions to analyze the connectivity patterns among the anatomic regions for a given cognitive task. We suggest a deep architecture which learns the natural groupings of the connectivity patterns of human brain in multiple time-resolutions. The suggested architecture is tested on task data set of Human Connectome Project (HCP) where we extract multi-resolution networks, each of which corresponds to a cognitive task. At the first level of this architecture, we decompose the fMRI signal into multiple sub-bands using wavelet decompositions. At the second level, for each sub-band, we estimate a brain network extracted from short time windows of the fMRI signal. At the third level, we feed the adjacency matrices of each mesh network at each time-resolution into an unsupervised deep learning algorithm, namely, a Stacked De- noising Auto-Encoder (SDAE). The outputs of the SDAE provide a compact connectivity representation for each time window at each sub-band of the fMRI signal. We concatenate the learned representations of all sub-bands at each window and cluster them by a hierarchical algorithm to find the natural groupings among the windows. We observe that each cluster represents a cognitive task with a performance of 93% Rand Index and 71% Adjusted Rand Index. We visualize the mean values and the precisions of the networks at each component of the cluster mixture. The mean brain networks at cluster centers show the variations among cognitive tasks and the precision of each cluster shows the within cluster variability of networks, across the subjects.