most citedMAG-GNN: Reinforcement Learning Boosted Graph Neural Network

5 citations · 6 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CL2024

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models

Ying Nie, Binwei Yan, Tianyu Guo +9

Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging and domain-specific task, such as finance, has not b…

cs.LG20235 cited

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Lecheng Kong, Jiarui Feng, Hao Liu +3

While Graph Neural Networks (GNNs) recently became powerful tools in graph learning tasks, considerable efforts have been spent on improving GNNs' structural encoding ability. A pa…

cs.LG2023

One for All: Towards Training One Graph Model for All Classification Tasks

Hao Liu, Jiarui Feng, Lecheng Kong +4

Designing a single model to address multiple tasks has been a long-standing objective in artificial intelligence. Recently, large language models have demonstrated exceptional capa…

cs.CV2023

Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects

Feng Yan, Xiaoheng Jiang, Yang Lu +5

Surface defect inspection is a very challenging task in which surface defects usually show weak appearances or exist under complex backgrounds. Most high-accuracy defect detection…

cs.CV20231 cited

CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation

Xiaoheng Jiang, Kaiyi Guo, Yang Lu +5

Surface defect inspection is of great importance for industrial manufacture and production. Though defect inspection methods based on deep learning have made significant progress,…

cs.LG2023

Graph Contrastive Learning Meets Graph Meta Learning: A Unified Method for Few-shot Node Tasks

Hao Liu, Jiarui Feng, Lecheng Kong +3

Graph Neural Networks (GNNs) have become popular in Graph Representation Learning (GRL). One fundamental application is few-shot node classification. Most existing methods follow t…