The sequential recommendation aims to predict users’ future interests or needs by analyzing
their behavioral data over some time. Most existing approaches model user preference in …

Large language models (LLMs) have achieved remarkable success in machine translation,
yet their performance on low-resource language pairs remains limited due to data scarcity …

Graph Collaborative Filtering discovers potential connections between users and items using
graph neural networks. However, graph neural networks may aggregate the noise in the …

The self-attention mechanism has been widely adopted in sequential recommendation due
to its powerful capability in modeling long-range dependencies. However, as the number of …

In sequencial recommendation, the expansion of Transformer layers often results in over-smoothing
phenomena, where the hidden representations of users become similar. The …

Graph-based collaborative filtering (GCF) models are hindered by data sparsity, long-tail
distributions, and over-smoothing caused by deep aggregation. To alleviate these challenges, …

Sequential recommendation aims to recommend the next item for a user to interact with by
analyzing the user’s historical interaction sequences. Recent studies have utilized attribute …

Edge computing plays a crucial role in supporting high-bandwidth and latency-sensitive
applications in the Artificial Intelligence of Things (AIoT). These applications often demand both …

A 1979 survey (1) in the Jianghua County of Hunan Province produced among 1283
subjects two hemoglobin variants which moved faster than Hb A during cellulose acetate …

Cement solidification technology can effectively reduce environmental pollution caused by
municipal solid waste incineration (MSWI) fly ash. The present study aimed at investigating …