Synergistic transGCN for aeroengine bearing skidding diagnosis under time-varying conditions
L Ma, B Jiang, N Lu, L **ao - IEEE Transactions on Industrial …, 2024 - ieeexplore.ieee.org
The demand for bearing skidding diagnosis is widely present in aeroengines operating at
high-speed and light-load conditions. However, the weak and time-varying characteristics of …
high-speed and light-load conditions. However, the weak and time-varying characteristics of …
[PDF][PDF] Buffalo: Enabling Large-Scale GNN Training via Memory-Efficient Bucketization
Graph Neural Networks (GNNs) have demonstrated outstanding results in many graph-
based deep-learning tasks. However, training GNNs on a large graph can be difficult due to …
based deep-learning tasks. However, training GNNs on a large graph can be difficult due to …
Multi-view graph transformer for waste of electric and electronic equipment classification and retrieval
A crucial first step to maximize the resource recovery in the end-of-(first)-life treatment of
Electric and Electronic Equipment (EEE) is the granular classification of product categories …
Electric and Electronic Equipment (EEE) is the granular classification of product categories …
A Survey of Graph Transformers: Architectures, Theories and Applications
Graph Transformers (GTs) have demonstrated a strong capability in modeling graph
structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as …
structures by addressing the intrinsic limitations of graph neural networks (GNNs), such as …
All-in-One: Heterogeneous Interaction Modeling for Cold-Start Rating Prediction
Cold-start rating prediction is a fundamental problem in recommender systems that has
been extensively studied. Many methods have been proposed that exploit explicit relations …
been extensively studied. Many methods have been proposed that exploit explicit relations …
Revisiting explicit recommendation with DC-GCN: Divide-and-Conquer Graph Convolution Network
F Peng, F Liao, X Lu, J Zheng, R Li - Information Systems, 2025 - Elsevier
Abstract In recent years, Graph Convolutional Networks (GCNs) have primarily been applied
to implicit feedback recommendation, with limited exploration in explicit scenarios. Although …
to implicit feedback recommendation, with limited exploration in explicit scenarios. Although …
Advancing Session-Based Recommendations with Atten-Mixer+: Dynamic and Adaptive Multi-Level Intent Mining
Session-based recommendation (SBR) systems, traditionally reliant on complex graph
neural networks (GNNs), often face challenges with marginal performance improvements …
neural networks (GNNs), often face challenges with marginal performance improvements …
Graph Neural Networks Are Evolutionary Algorithms
K Ouyang, S Fu - arxiv preprint arxiv:2412.17629, 2024 - arxiv.org
In this paper, we reveal the intrinsic duality between graph neural networks (GNNs) and
evolutionary algorithms (EAs), bridging two traditionally distinct fields. Building on this …
evolutionary algorithms (EAs), bridging two traditionally distinct fields. Building on this …
Contrastive Learning Meets Pseudo-label-assisted Mixup Augmentation: A Comprehensive Graph Representation Framework from Local to Global
J Wang, Y Sun, J Wang, J Gao, S Wang… - arxiv preprint arxiv …, 2025 - arxiv.org
Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness in various
graph representation learning tasks. However, most existing GNNs focus primarily on …
graph representation learning tasks. However, most existing GNNs focus primarily on …
GVTNet: Graph Vision Transformer For Face Super-Resolution
C Yang, Y Fan, C Lu, M Yuan, Z Yang - arxiv preprint arxiv:2502.12570, 2025 - arxiv.org
Recent advances in face super-resolution research have utilized the Transformer
architecture. This method processes the input image into a series of small patches …
architecture. This method processes the input image into a series of small patches …