Venus Haghighi

Mrs. Venus Haghighi

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 January 2024 in IEEE Transactions on Artificial Intelligence
Verified
Journal Article
Closed access
NSNasrin Shabani
Nasrin Shabani
Jia WUJia WU
Jia WU
ABAmin Beheshti
Amin Beheshti
Michael ShengMichael Sheng
Michael Sheng
JFJin Foo
Jin Foo
MSMaryam Shahabikargar
Maryam Shahabikargar
As large-scale graphs become more widespread, more and more computational challenges with extracting, processing, and interpreting large graph data are being exposed. It is therefore natural to search for ways to summarize these expansive graphs while preserving their key characteristics. In the past, most graph summarization techniques sought to capture the most important part of a graph statistically. However, today, the high dimensionality and complexity of modern graph data are making deep learning techniques more popular. Hence, this paper presents a comprehensive survey of progress in deep learning summarization techniques that rely on graph neural networks (GNNs). Our investigation includes a review of the current state-of-the-art approaches, including recurrent GNNs, convolutional GNNs, graph autoencoders, and graph attention networks. A new burgeoning line of research is also discussed where graph reinforcement learning is being used to evaluate and improve the quality of graph summaries. Additionally, the survey provides details of benchmark datasets, evaluation metrics, and open-source tools that are often employed in experimentation settings, along with a detailed comparison, discussion, and takeaways for the research community focused on graph summarization. Finally, the survey concludes with a number of open research challenges to motivate further study in this area.

12 June 2025 in Information
Verified
Journal Article
Open access
PDF file
Asma AlkalbaniAsma Alkalbani
Asma Alkalbani
AAAhmed Salim Alrawahi
Ahmed Salim Alrawahi
Ahmad SalahAhmad Salah
Ahmad Salah
VHVenus Haghighi
Venus Haghighi
YZYang Zhang
Yang Zhang
Michael ShengMichael Sheng
Michael Sheng
This systematic review evaluates recent literature from January 2021 to March 2024 on large language model (LLM) applications across diverse medical specialties. Searching PubMed, Web of Science, and Scopus, we included 84 studies. LLMs were applied to tasks such as clinical natural language processing, medical decision support, education, and aiding diagnostic processes. While studies reported benefits such as improved efficiency and, in some specific NLP tasks, high accuracy above 90%, significant challenges persist concerning reliability, ethical implications, and performance consistency, with accuracy in broader diagnostic support applications showing substantial variability, with some as low as 3%. The overall risk of bias in the reviewed literature was considerably low in 72 studies. Key findings highlight a substantial heterogeneity in LLM performance across different medical tasks and contexts, preventing meta-analysis due to a lack of standardized methodologies. Future efforts should prioritize developing domain-specific LLMs using robust medical data and establishing rigorous validation standards to ensure their safe and effective clinical integration. Trial registration: PROSPERO (CRD42024561381).

1 August 2023
Verified
Conference Paper
Open access
PDF file
BSBehnaz Soltani
Behnaz Soltani
YZYipeng Zhou
Yipeng Zhou
VHVenus Haghighi
Venus Haghighi
JLJohn C. S. Lui
John C. S. Lui
In traditional machine learning, it is trivial to conduct model evaluation since all data samples are managed centrally by a server. However, model evaluation becomes a challenging problem in federated learning (FL), which is called federated evaluation in this work. This is because clients do not expose their original data to preserve data privacy. Federated evaluation plays a vital role in client selection, incentive mechanism design, malicious attack detection, etc. In this paper, we provide the first comprehensive survey of existing federated evaluation methods. Moreover, we explore various applications of federated evaluation for enhancing FL performance and finally present future research directions by envisioning some challenges.

21 October 2024
Verified
Conference Paper
Open access
BSBehnaz Soltani
Behnaz Soltani
VHVenus Haghighi
Venus Haghighi
YZYipeng Zhou
Yipeng Zhou
Michael ShengMichael Sheng
Michael Sheng
LYLina Yao
Lina Yao
Federated learning (FL) is a distributed machine learning paradigm in which clients collaboratively train models in a privacy-preserving manner. While centralized FL (CFL) suffers from single points of failure and performance bottlenecks, decentralized FL (DFL), which depends on inter-client communication, has emerged to eliminate the need of a central entity. However, due to lack of the coordination of a central server, heterogeneous data distribution across clients makes local models in DFL inclined to diverge towards their local objectives, resulting in poor model accuracy. Moreover, each client in DFL needs to communicate with multiple neighbors, yielding a heavy communication load. To tackle these challenges, we propose a novel DFL framework called DFLStar, which can improve DFL from two perspectives. First, to avoid significantly diverging towards local data, DFLStar incorporates self-knowledge distillation to enhance the local model training by assimilating knowledge from the aggregated model. Second, clients in DFLStar identify and only select the most informative neighbors (based on the last layer model similarity) for parameter exchange, thereby minimizing the communication overhead. Our experimental results on two real datasets demonstrate that DFLStar significantly improves both communication overhead and training time compared to traditional DFL algorithms while achieving a specific target accuracy. Furthermore, within a fixed training duration, DFLStar constantly obtains the highest model accuracy compared to the baselines.

28 May 2025 in Knowledge and Information Systems
Verified
Journal Article
Open access
PDF file
VHVenus Haghighi
Venus Haghighi
BSBehnaz Soltani
Behnaz Soltani
NSNasrin Shabani
Nasrin Shabani
Jia WUJia WU
Jia WU
YZYang Zhang
Yang Zhang
Michael ShengMichael Sheng
Michael Sheng
Fraud detection in online networks has become increasingly challenging as fraudsters adopt sophisticated camouflage tactics to evade detection, making it imperative to combat their deceptive strategies. Graph-based fraud detection has gained significant attention in recent years, reflecting its growing potential to mitigate sophisticated fraudulent activities. The main objective of graph-based fraud detection is to distinguish between fraudsters and normal entities within graphs. While real-world networks contain complex, high-order relationships, existing graph-based fraud detection methods focus solely on pairwise interactions, overlooking non-pairwise relationships and the broader dependencies among entities within fraud graphs. Thus, we highlight the importance of exploring non-pairwise relationships to build a more effective fraud detection model. In this paper, we propose TROPICAL, a novel TRansfOrmer-based hyPergraph LearnIng framework for detecting CAmouflaged maLicious actors in online social networks. To capture comprehensive high-order relations, we construct a hypergraph from the original input graph. However, constructing the hypergraph can be computationally intensive. TROPICAL addresses this challenge by carefully selecting moderate hyperparameters, creating a balance between computational efficiency and effectively capturing high-order relationships. TROPICAL learns node representations by processing multiple hyperedge groups and incorporates positional encodings into the aggregated information to enhance their distinctiveness. The aggregated sequential information is then passed through a transformer encoder, enabling the model to generate rich, high-order representations to detect camouflaged fraudsters. Extensive experiments on two real-world datasets demonstrate TROPICAL’s superior performance compared to the state-of-the-art fraud detection models. The source codes and the datasets of our work are available at https://github.com/VenusHaghighi/TROPICAL.

11 June 2024 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
NSNasrin Shabani
Nasrin Shabani
ABAmin Beheshti
Amin Beheshti
AJAlireza Jolfaei
Alireza Jolfaei
Jia WUJia WU
Jia WU
VHVenus Haghighi
Venus Haghighi
JFJin Foo
Jin Foo
Efficiently processing large-scale graphs for information retrieval tasks presents a formidable hurdle, demanding innovative solutions for enhancing user experiences. This paper introduces a framework that merges attention-based graph summarization with state-of-the-art graph sampling methods tailored explicitly for large-scale graph processing and information retrieval applications, all aimed at enriching user experiences. Our approach distinguishes itself through its adeptness in efficiently handling vast graph datasets, leveraging robust sampling techniques and attention mechanisms to enhance feature extraction. Central to our methodology is the utilization of graph summarization techniques, which focus on distilling pertinent information, thereby enhancing both the accuracy and computational efficiency of information retrieval and recommendation tasks. Through practical demonstrations, notably within academic databases, our framework showcases its effectiveness in real-world scenarios, offering a significant advancement in the realm of personal technology data management and information retrieval systems.