همایش بین المللی هوش مصنوعی

صفحه اصلی / دومین همایش بین المللی هوش مصنوعی

Attention-Driven Deep Generative Modeling of Temporal Networks

نویسندگان :

Maryam Lotfali Kani¹ Sadegh Aliakbary² Hamed Malek³

1- دانشگاه شهید بهشتی 2- دانشگاه شهید بهشتی 3- دانشگاه شهید بهشتی

کلمات کلیدی :

complex networks،temporal networks،network models،deep generative models،attention mechanism

چکیده :

Deep generative models have been widely applied to complex network generation, enabling the synthesis of structures that closely resemble real-world systems. Among these models, temporal network models capture time-varying interactions by allowing nodes and edges to appear or change over time. In this work, we enhance LSTM-based temporal network generation by incorporating self-attention mechanisms in two separate models, namely pre-LSTM and post-LSTM models, to better capture long-range temporal dependencies and improve model accuracy. The proposed model is evaluated on six real-world temporal networks—Bitcoin, Wikipedia, Calls, Movies, MathOverflow, and Wikipedia Edits—using structural metrics such as mean degree, wedge count, power-law exponent, clustering coefficient, and centrality measures. Experimental results show that the attention-augmented model significantly reduces generation error for networks with long temporal spans, while networks with shorter temporal ranges may exhibit marginal performance degradation due to limited temporal signal strength.

لیست مقالات

لیست مقالات بایگانی شده

Interpretable Ensemble Learning for Predicting the Non-linear Moment Capacity of Bolted Extended Endplate Moment Connections

Matin Alizadeh - ُS.Mohammad Hosseini - .Mahmoud. R Shiravand

AdaLayer-CAM: Adaptive Multi-Layer Method for Visualization and Explanation of CNNs

MohammadJavad GhaderiPoor - Latifeh PourMohammadBagher - Zahra Rahimi

Ensemble Machine Learning for Predicting Stroke Patient Survival

Seyedeh Maryam Mousavi - Samira Ahmadi - Solmaz Norouzi

Studying the Impact of Artificial Intelligence in the Judicial System

Mahdi Rajaeian - Shadi Chegini

A Systematic Review of Tokenizer Adaption Techniques for Large Language Models

Niloofar Mortazavi - Mostafa Amiri - Hesham Faili

DC-GATT: Dynamic Connectivity Graph Attention Transformer for Multi-Task EEG Classification

Mohammad Ahadzadeh - Pouya Taghipour Langrodi - Arian Afshar - Golnaz Baghdadi

Fibroglandular Tissue Classification in Breast MRI: A Comparative Study of Automated Decision Strategies

Meysam Khalaj - Arvin Arian - Ala Torabi - Nasrin Ahmadinejad - Masoumeh Gity - Seyedeh Nooshin Miratashi Yazdi - Mohammad Pooya Afshari - Melika Sadeghi Tabrizi - Hamid Soltanian-Zadeh

A Deep Reinforcement Learning Approach to Automated Stock Trading, using xLSTM Networks

Faezeh Sarlakifar - Mohammadreza Mohammadzadeh Asl - Sajjad Rezvani Khaledi - Armin Salimi-Badr

Enhancing Facial Emotion Recognition Using YOLO11 Classification on the AffectNet Dataset

Reza Nasiri - Seyed Enayat Alavi - Mohammad Javad Rashti

Community-Aware Influence Maximization on Heterogeneous Information Networks using Graph Neural Networks

Amirreza Vafaei - Sadegh Aliakbary

بیشتر