Hojat Allah Salehi
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
Hojat Allah Salehi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Farhad Shirani
Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL, USA
2 shared publications Babak Tavassoli
Faculty of Electrical Engineering K.N. Toosi University of Technology Tehran Iran
1 shared publication- Dongsheng Luo
Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL, USA
1 shared publication - Esteban Schafir
Florida International University
1 shared publication - Jiaxing Zhang
New Jersey Institute of Technology, USA
1 shared publication - Jingchao Ni
University of Houston, Houston, USA
1 shared publication
Latest Publications
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-16
Addressing Structural Distribution Shift in Explanations for Graph Neural Networks
Graph Neural Networks (GNNs) are essential for processing graph-structured data and have wide applications in critical domains. The increasing use of GNNs in high-stakes scenarios requires robust explainability to ensure trust and transparency in decision-making. A common approach to explaining GNNs is to identify subgraphs, a.k.a. explanations, that significantly influence model predictions. However, this task is challenging due to the distribution shifts from the original training graphs to the explanation subgraphs, a factor that is largely overlooked in the existing research. These shifts arise because GNNs are trained on original graphs, while explanation subgraphs often differ in properties such as the number of nodes or structural patterns. As a result, GNNs may struggle to generalize to explanation subgraphs with a different distribution from its training data. In this paper, we systematically investigate the Out-Of-Distribution (OOD) problem through theoretical analysis and empirical studies. To address this challenge, we first develop a theoretical framework that formalizes the notion of explanation subgraphs through sufficiency and minimality criteria, ensuring both prediction preservation and structural compactness. Our analysis reveals a fundamental distributional disparity between explanation subgraphs and original graphs, leading to a novel concept of proxy graphs proposed in this work. Proxy graphs maintain the essential explanatory information while conforming to the original data distribution through a combination of parametric and non-parametric optimization approaches. Empirical evaluations on diverse datasets show that our method improves the quality and reliability of GNN explanations, advancing the field of GNN explainability.
- 4 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1-16
Addressing Structural Distribution Shift in Explanations for Graph Neural Networks
Graph Neural Networks (GNNs) are essential for processing graph-structured data and have wide applications in critical domains. The increasing use of GNNs in high-stakes scenarios requires robust explainability to ensure trust and transparency in decision-making. A common approach to explaining GNNs is to identify subgraphs, a.k.a. explanations, that significantly influence model predictions. However, this task is challenging due to the distribution shifts from the original training graphs to the explanation subgraphs, a factor that is largely overlooked in the existing research. These shifts arise because GNNs are trained on original graphs, while explanation subgraphs often differ in properties such as the number of nodes or structural patterns. As a result, GNNs may struggle to generalize to explanation subgraphs with a different distribution from its training data. In this paper, we systematically investigate the Out-Of-Distribution (OOD) problem through theoretical analysis and empirical studies. To address this challenge, we first develop a theoretical framework that formalizes the notion of explanation subgraphs through sufficiency and minimality criteria, ensuring both prediction preservation and structural compactness. Our analysis reveals a fundamental distributional disparity between explanation subgraphs and original graphs, leading to a novel concept of proxy graphs proposed in this work. Proxy graphs maintain the essential explanatory information while conforming to the original data distribution through a combination of parametric and non-parametric optimization approaches. Empirical evaluations on diverse datasets show that our method improves the quality and reliability of GNN explanations, advancing the field of GNN explainability.
- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 71 (10) , 8048-8079
On Non-Interactive Simulation of Distributed Sources With Finite Alphabets
This work presents a Fourier analysis framework for the non-interactive source simulation (NISS) problem. Two distributed agents observe a pair of sequences$X^{d}$ and$Y^{d}$ drawn according to a joint distribution$P_{X^{d}Y^{d}}$ . The agents aim to generate outputs$U=f_{d}(X^{d})$ and$V=g_{d}(Y^{d})$ with a joint distribution sufficiently close in total variation to a target distribution$Q_{UV}$ . Existing works have shown that the NISS problem with finite-alphabet outputs is decidable. For the binary-output NISS, an upper-bound to the input complexity was derived which is$O\left ({{\exp \mathrm {poly}\left ({{\frac {1}{\epsilon }}}\right)}}\right)$ . In this work, the input complexity and algorithm design are addressed in several classes of NISS scenarios. For binary-output NISS scenarios with doubly-symmetric binary inputs, it is shown that the input complexity is$\Theta \left ({{\log {\frac {1}{\epsilon }}}}\right)$ , thus providing a super-exponential improvement in input complexity. An explicit characterization of the simulating pair of functions is provided. For general finite-input scenarios, a constructive algorithm is introduced that explicitly finds the simulating functions$(f_{d}(X^{d}),g_{d}(Y^{d}))$ . The approach relies on a novel Fourier analysis framework. Various numerical simulations of NISS scenarios with IID inputs are provided. Furthermore, to illustrate the general applicability of the Fourier framework, several examples with non-IID inputs, including entanglement-assisted NISS and NISS with Markovian inputs are provided.- 11 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 71 (10) , 8048-8079
On Non-Interactive Simulation of Distributed Sources With Finite Alphabets
This work presents a Fourier analysis framework for the non-interactive source simulation (NISS) problem. Two distributed agents observe a pair of sequences$X^{d}$ and$Y^{d}$ drawn according to a joint distribution$P_{X^{d}Y^{d}}$ . The agents aim to generate outputs$U=f_{d}(X^{d})$ and$V=g_{d}(Y^{d})$ with a joint distribution sufficiently close in total variation to a target distribution$Q_{UV}$ . Existing works have shown that the NISS problem with finite-alphabet outputs is decidable. For the binary-output NISS, an upper-bound to the input complexity was derived which is$O\left ({{\exp \mathrm {poly}\left ({{\frac {1}{\epsilon }}}\right)}}\right)$ . In this work, the input complexity and algorithm design are addressed in several classes of NISS scenarios. For binary-output NISS scenarios with doubly-symmetric binary inputs, it is shown that the input complexity is$\Theta \left ({{\log {\frac {1}{\epsilon }}}}\right)$ , thus providing a super-exponential improvement in input complexity. An explicit characterization of the simulating pair of functions is provided. For general finite-input scenarios, a constructive algorithm is introduced that explicitly finds the simulating functions$(f_{d}(X^{d}),g_{d}(Y^{d}))$ . The approach relies on a novel Fourier analysis framework. Various numerical simulations of NISS scenarios with IID inputs are provided. Furthermore, to illustrate the general applicability of the Fourier framework, several examples with non-IID inputs, including entanglement-assisted NISS and NISS with Markovian inputs are provided.- 9 September 2020
- Published by Wiley in Optimal Control Applications and Methods
- Vol. 41 (6) , 1854-1874
A gradient algorithm for solution of the optimal control problem for hybrid switching systems
Summary: In this article, an algorithm is presented for solving the optimal control problem for the general form of a hybrid switching system. The cost function comprises terminal, running and switching costs. The controlled system is an autonomous hybrid switching system with jumps either at some switching times or some time varying switching manifolds. The proposed algorithm is an extension of the first‐order gradient method for the conventional optimal control problem. The algorithm requires a low computational effort. The system's dynamical equations together with a set of algebraic equations are solved at each iteration in order to find the descent direction. The convergence of algorithm is proved and examples are provided to demonstrate the efficiency of the algorithm for different types of hybrid switching system optimal control problems.
- 9 September 2020
- Published by Wiley in Optimal Control Applications and Methods
- Vol. 41 (6) , 1854-1874
A gradient algorithm for solution of the optimal control problem for hybrid switching systems
Summary: In this article, an algorithm is presented for solving the optimal control problem for the general form of a hybrid switching system. The cost function comprises terminal, running and switching costs. The controlled system is an autonomous hybrid switching system with jumps either at some switching times or some time varying switching manifolds. The proposed algorithm is an extension of the first‐order gradient method for the conventional optimal control problem. The algorithm requires a low computational effort. The system's dynamical equations together with a set of algebraic equations are solved at each iteration in order to find the descent direction. The convergence of algorithm is proved and examples are provided to demonstrate the efficiency of the algorithm for different types of hybrid switching system optimal control problems.