[HTML][HTML] Applications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review

I Malashin, V Tynchenko, A Gantimurov, V Nelyub… - …, 2024 - pmc.ncbi.nlm.nih.gov
This review explores the application of Long Short-Term Memory (LSTM) networks, a
specialized type of recurrent neural network (RNN), in the field of polymeric sciences. LSTM …

A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges

ZZ Feng, R Wang, TX Wang, M Song, S Wu… - arXiv preprint arXiv …, 2024 - arxiv.org
Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to
capture structural, temporal, and contextual relationships in dynamic graphs simultaneously …

Out-of-distribution generalized dynamic graph neural network with disentangled intervention and invariance promotion

Z Zhang, X Wang, Z Zhang, H Li, W Zhu - arXiv preprint arXiv:2311.14255, 2023 - arxiv.org
Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities
by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to …

SCFL: Spatio-temporal consistency federated learning for next POI recommendation

L Zhong, J Zeng, Z Wang, W Zhou, J Wen - Information Processing & …, 2024 - Elsevier
Existing personalized federated learning frameworks fail to significantly improve the
personalization of user preference learning in next Point-Of-Interest (POI) recommendations …

Global and local hypergraph learning method with semantic enhancement for POI recommendation

J Zeng, H Tao, H Tang, J Wen, M Gao - Information Processing & …, 2025 - Elsevier
The deep semantic information mining extracts deep semantic features from textual data and
effectively utilizes the world knowledge embedded in these features, so it is widely …

Disentangled Dynamic Graph Attention Network for Out-of-Distribution Sequential Recommendation

Z Zhang, X Wang, H Chen, H Li, W Zhu - ACM Transactions on …, 2024 - dl.acm.org
Sequential recommendation, leveraging user-item interaction histories to provide
personalized and timely suggestions, has drawn significant research interest recently. With …

SFTe: Temporal knowledge graphs embedding for future interaction prediction

W Jia, R Ma, W Niu, L Yan, Z Ma - Information Systems, 2024 - Elsevier
Interaction prediction is a crucial task in the Social Internet of Things (SIoT), serving diverse
applications including social network analysis and recommendation systems. However, the …

Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach

Y Li, Y Yang, J Cao, S Liu, H Tang, G Xu - Proceedings of the 30th ACM …, 2024 - dl.acm.org
Recent studies successfully learned static graph embeddings that are structurally fair by
preventing the effectiveness disparity of high-and low-degree vertex groups in downstream …

TCGC: Temporal Collaboration-Aware Graph Co-Evolution Learning for Dynamic Recommendation

H Tang, S Wu, X Sun, J Zeng, G Xu, Q Li - ACM Transactions on …, 2024 - dl.acm.org
Dynamic recommendation systems, where users interact with items continuously over time,
have been widely deployed in real-world online streaming applications. The burst of …

DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs

J Zhang, J Chen, M Yang, A Feng, S Liang… - arXiv preprint arXiv …, 2024 - arxiv.org
Dynamic text-attributed graphs (DyTAGs) are prevalent in various real-world scenarios,
where each node and edge are associated with text descriptions, and both the graph …