132 citations · 683 across the 107 of their papers we have counts for
36 papers · 1 filter
Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification
Jiajun Zhou, Yadong Li, Xuanze Chen +4
Mixture-of-Experts (MoE) architectures offer a scalable path for Graph Neural Networks (GNNs) in node classification tasks but typically rely on static and rigid routing strategies…
CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning
Xuanze Chen, Jiajun Zhou, Yadong Li +2
Heterogeneous graph representation learning (HGRL) is essential for modeling complex systems with diverse node and edge types. However, most existing methods are limited to closed-…
The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
Yao Lu, Yuqi Li, Wenbin Xie +4
Although large language models (LLMs) have achieved revolutionary breakthroughs in many fields, their large model size and high computational cost pose significant challenges for p…
LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE Methods
Shaoheng Wang, Yao Lu, Yuqi Li +5
As a parameter efficient fine-tuning (PEFT) method, low-rank adaptation (LoRA) can save significant costs in storage and computing, but its strong adaptability to a single task is…
SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing
Qiuhao Liu, Ling Li, Yao Lu +3
Deep neural networks tend to memorize noisy labels, severely degrading their generalization performance. Although Mixup has demonstrated effectiveness in improving generalization a…
\emph{FoQuS}: A Forgetting-Quality Coreset Selection Framework for Automatic Modulation Recognition
Yao Lu, Chunfeng Sun, Dongwei Xu +3
Deep learning-based Automatic Modulation Recognition (AMR) model has made significant progress with the support of large-scale labeled data. However, when developing new models or…
DUSE: A Data Expansion Framework for Low-resource Automatic Modulation Recognition based on Active Learning
Yao Lu, Hongyu Gao, Zhuangzhi Chen +4
Although deep neural networks have made remarkable achievements in the field of automatic modulation recognition (AMR), these models often require a large amount of labeled data fo…
FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition
Yao Lu, Tengfei Ma, Zeyu Wang +5
With the rapid development of wireless communications and the growing complexity of digital modulation schemes, traditional manual modulation recognition methods struggle to extrac…
Adaptive Substructure-Aware Expert Model for Molecular Property Prediction
Tianyi Jiang, Zeyu Wang, Shanqing Yu +1
Molecular property prediction is essential for applications such as drug discovery and toxicity assessment. While Graph Neural Networks (GNNs) have shown promising results by model…
Mixture of Message Passing Experts with Routing Entropy Regularization for Node Classification
Xuanze Chen, Jiajun Zhou, Yadong Li +3
Graph neural networks (GNNs) have achieved significant progress in graph-based learning tasks, yet their performance often deteriorates when facing heterophilous structures where c…
Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
Xuanze Chen, Jiajun Zhou, Shanqing Yu +1
Graph neural networks excel at graph representation learning but struggle with heterophilous data and long-range dependencies. And graph transformers address these issues through s…
Reassessing Layer Pruning in LLMs: New Insights and Methods
Yao Lu, Hao Cheng, Yujie Fang +6
Although large language models (LLMs) have achieved remarkable success across various domains, their considerable scale necessitates substantial computational resources, posing sig…
RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively
Yao Lu, Peixin Zhang, Jingyi Wang +3
Deep learning has revolutionized computing in many real-world applications, arguably due to its remarkable performance and extreme convenience as an end-to-end solution. However, d…
Rethinking Graph Transformer Architecture Design for Node Classification
Jiajun Zhou, Xuanze Chen, Chenxuan Xie +3
Graph Transformer (GT), as a special type of Graph Neural Networks (GNNs), utilizes multi-head attention to facilitate high-order message passing. However, this also imposes severa…
Network Anomaly Traffic Detection via Multi-view Feature Fusion
Song Hao, Wentao Fu, Xuanze Chen +4
Traditional anomalous traffic detection methods are based on single-view analysis, which has obvious limitations in dealing with complex attacks and encrypted communications. In th…
MDM: Advancing Multi-Domain Distribution Matching for Automatic Modulation Recognition Dataset Synthesis
Dongwei Xu, Jiajun Chen, Yao Lu +5
Recently, deep learning technology has been successfully introduced into Automatic Modulation Recognition (AMR) tasks. However, the success of deep learning is all attributed to th…
Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision
Chenxiang Jin, Jiajun Zhou, Chenxuan Xie +3
The rampant fraudulent activities on Ethereum hinder the healthy development of the blockchain ecosystem, necessitating the reinforcement of regulations. However, multiple imbalanc…
A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models
Yao Lu, Yutao Zhu, Yuqi Li +4
With the successful application of deep learning in communications systems, deep neural networks are becoming the preferred method for signal classification. Although these models…
A Federated Parameter Aggregation Method for Node Classification Tasks with Different Graph Network Structures
Hao Song, Jiacheng Yao, Zhengxi Li +6
Over the past few years, federated learning has become widely used in various classical machine learning fields because of its collaborative ability to train data from multiple sou…
Augmenting Radio Signals with Wavelet Transform for Deep Learning-Based Modulation Recognition
Tao Chen, Shilian Zheng, Kunfeng Qiu +3
The use of deep learning for radio modulation recognition has become prevalent in recent years. This approach automatically extracts high-dimensional features from large datasets,…
RK-core: An Established Methodology for Exploring the Hierarchical Structure within Datasets
Yao Lu, Yutian Huang, Jiaqi Nie +2
Recently, the field of machine learning has undergone a transition from model-centric to data-centric. The advancements in diverse learning tasks have been propelled by the accumul…
PathMLP: Smooth Path Towards High-order Homophily
Jiajun Zhou, Chenxuan Xie, Shengbo Gong +4
Real-world graphs exhibit increasing heterophily, where nodes no longer tend to be connected to nodes with the same label, challenging the homophily assumption of classical graph n…
Subgraph Networks Based Contrastive Learning
Jinhuan Wang, Jiafei Shao, Zeyu Wang +3
Graph contrastive learning (GCL), as a self-supervised learning method, can solve the problem of annotated data scarcity. It mines explicit features in unannotated graphs to genera…
Clarify Confused Nodes via Separated Learning
Jiajun Zhou, Shengbo Gong, Xuanze Chen +4
Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented tasks. However, real-world graphs invariably contain a certain proportion of heterophilous nodes, c…