Saba A. Al-Sayouri
Ph.D. Candidate in Industrial & Systems Engineering at SUNY Binghamton

Systems Science & Industrial Engineering Department
State University of New York at Binghamton
Bingahmton, NY

Email: ssyouri1 [at] binghamton [dot] edu

Google Scholar


About Me

I am Saba Al-Sayouri, a fourth-year PhD candidate in the Systems Science and Industrial Engineering Department at State University of New York at Binghamton. I am working with Prof. Sara Lam, and currently, a visiting scholar at University of California, Riverside and hosted by Prof. Evangelos Papalexakis in the Department of Computer Science. My research interest lies in studying and developing algorithmic frameworks for mining large-scale graphs. In particular, I am obsessed with developing algorithms that learn node representations in real-world networks.


September 2018
Invited to attend the 2018 INFORMS Doctoral Student Colloquium.
June 2018
Our paper on learning large-scale network representations accepted at ASONAM.
June 2018
Our paper on learning large-scale network representations using tensor decomposition accepted at the 14th International Workshop on Mining and Learning with Graphs.
November 2017
Awarded Binghamton foundation travel award!
August 2017
Attended KDD 2017. Halifax, Canada.
July 2017
Awarded student travel grant to attend KDD 2017!
June 2017
Our paper on learning node representation accepted at the 13th International Workshop on Mining and Learning with Graphs.
April 2017
Awarded student travel grant to attend ICDE 2017 Women in Data Science and Engineering Workshop!
May 2016
Attended ISERC 2016. Anaheim, CA.
March 2016
Our paper on logistics and supply chain won best student paper award at 2016 ISERC!
February 2016
Our paper on logistics and supply chain accepted at ISERC 2016.



t-PINE: Tensor-based Predictable and Interpretable Node Embeddings arxiv

Saba A Al-Sayouri, Ekta Gujral, Danai Koutra, Evangelos E Papalexakis, Sarah S Lam
Preprint 2018


GECS: Graph Embedding Using Connection Subgraphs MLG '17

Saba A Al-Sayouri, Pravallika Devineni, Sarah S Lam, Evangelos E Papalexakis, Danai Koutra
13th International Workshop on Mining and Learning with Graphs (MLG '17)

This paper studies the problem of learning large-scale graph representations (a.k.a. embeddings). Such representations encode the relations among distinct nodes on the continuous feature space. The learned representations generalize over various tasks, such as node classification, link prediction, and recommendation. Learning nodes representations aims to map proximate nodes close to one another in the low-dimension vector space. Thus, embedding algorithms pursue to preserve local and global network structure by identifying nodes neighborhood notions. However, the means proposed methods have been employed in order to identify nodes neighborhoods fail to precisely capture network structure. In this paper, we propose a novel scalable graph embedding algorithmic framework called GECS, which aims to learn graph representations using connection subgraphs, where analogy with electrical circuits has been employed. Th connection subgraphs are created to address the proximity among each two non-adjacent nodes, which are abundant in real-world networks, by maximizing the amount of flow between them. Although a subgraph captures proximity between two non-adjacent nodes, the formation of the subgraph addresses the direct connections with immediate neighbors as well. Therefore, our algorithm better preserves the local and global structure of a network. Further, despite the fact that non-adjacent nodes are numerous in real-world networks, our algorithm can scale to large-scale graphs, because we do not deal with the graph as a whole, instead, with much more smaller extracted subgraphs. Since our algorithm is not yet empirically examined, we here introduce a potential solution that can better learn graph representations comparing to existing embedding methods accompanied by rational reasoning.
title={GECS: Graph Embedding Using Connection Subgraphs},
author={Saba Al-Sayouri, Pravallika Devineni, Sarah Lam, Vagelis Papalexakis and Danai Koutra},
booktitle={Proceedings of the 13th International Workshop on Mining and Learning with Graphs (MLG)},

A Clinical Decision Support System for Malignant Pleural Effusion Analysis ISERC '16

Troy J Vargason, Joshua Cohn, David Rios, Olivia Schultz, Joseph Cleary, Dennis Lau, Walker Land, J David Schaffer, Yinglei Li, Chun-An Chou, Saba A Al-Sayouri, Jagmohan S Sidhu, Martha F Nelson, Xingye Qiao
Industrial and Systems Engineering Research Conference/IIE Annual Conference & Expo 2016 (ISERC '16).

Pleural effusion occurs when fluid accumulates in the pleural cavity surrounding the lung. This condition is commonly caused by infection, but can also be associated with the presence of a metastatic tumor. Samples of pleural fluid are used to analyze the morphologies of mesothelial cells and can typically be used to make a diagnosis between benignity and malignancy. Atypical pleural effusion samples are not easily identified as benign or malignant due to a lack of differentiable visual features, and such a problem has a significant influence in clinicians' decision making. In this paper, the goal is to develop a clinical decision support system (CDSS) using computer imaging and machine learning techniques for diagnosing atypical pleural effusion. The proposed approach involves four steps for analyzing slides of pleural effusion samples: image processing, feature measurement, feature selection, and classification. Processing and measurement of images produced a preliminary data set of 500 samples; each is described by 398 features. A genetic algorithm was applied for feature selection and identified a subset of 39 important features. The experimental results showed that the selected features can distinguish atypical nuclei as benign or malignant with a five-fold cross validation accuracy of 91%.
title={A Clinical Decision Support System for Malignant Pleural Effusion Analysis},
author={Vargason, Troy J and Cohn, Joshua and Rios, David and Schultz, Olivia and Cleary, Joseph and Lau, Dennis and Land, Walker and Schaffer, J David and Li, Yinglei and Chou, Chun-An and others},

Robust-Optimization Models of Buyer-Vendor Inventory for Supply Chain Coordination ISERC '16

Saba A. Al-Sayouri, Yinglei Li, Amro N Khasawneh, Qianqian Zhang, Nagendra N Nagarur
Industrial and Systems Engineering Research Conference/IIE Annual Conference & Expo 2016 (ISERC '16).

Recently the risk and uncertainty levels of the supply chains (SC) have increased due to various factors, such as globalization. Additionally, SC members are dependent and correlated to each other in terms of information and resources. Therefore, supply chain coordination (SCC) has become more important. Buyer-vendor inventory management is one of the main areas of SCC. In most buyer-vendor inventory models, the unit stockholding cost in each time period is considered as a constant parameter. However, the uncertainty of unit stockholding cost often exists in reality. The objective of this paper is to enhance the decision model’s robustness by explicitly considering the uncertainty of unit stockholding cost. A robust model of buyer-vendor inventory is proposed by applying robust optimization. Specifically, a robust counterpart of unit stockholding cost is addressed in the model. A parameter, Γ, is used to control the degree of conservatism or robustness of the solution. Four scenarios are simulated to test the deterministic and robust models. Corresponding results are presented.
title={Robust-Optimization Models of Buyer-Vendor Inventory for Supply Chain Coordination},
author={Syouri, Saba A and Li, Yinglei and Khasawneh, Amro N and Zhang, Qianqian and Nagarur, Nagendra N},

Professional Certificates

March 2013
Lean Six Sigma Green Belt Certified, Binghamton University
November 2016
Lean Six Sigma Black Belt Certified, Binghamton University


Welcome! you are the acesso gratis th vistor of my homepage.

Free Visitor Maps at
Get a FREE visitor map for your site!