7 papers
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
Yuting Zhang, Yanbei Liu, Zhitao Xiao +3
Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted wides…
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
Jingren Liu, Zhong Ji, YunLong Yu +4
Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting probl…
Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts
Zhong Ji, Rongshuai Wei, Jingren Liu +2
Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce s…
HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport
Yanbei Liu, Chongxu Wang, Zhitao Xiao +3
Heterogeneous Graph Neural Networks (HGNNs), have demonstrated excellent capabilities in processing heterogeneous information networks. Self-supervised learning on heterogeneous gr…
iEBAKER: Improved Remote Sensing Image-Text Retrieval Framework via Eliminate Before Align and Keyword Explicit Reasoning
Yan Zhang, Zhong Ji, Changxu Meng +2
Recent studies focus on the Remote Sensing Image-Text Retrieval (RSITR), which aims at searching for the corresponding targets based on the given query. Among these efforts, the ap…
Optimal Transport Adapter Tuning for Bridging Modality Gaps in Few-Shot Remote Sensing Scene Classification
Zhong Ji, Ci Liu, Jingren Liu +3
Few-Shot Remote Sensing Scene Classification (FS-RSSC) presents the challenge of classifying remote sensing images with limited labeled samples. Existing methods typically emphasiz…