Ganqu Cui

Publications11
h-index4
Citations1,701
Highly Influential Citations113
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • Maosong Sun
  • 419 Publications • 17,998 Citations
  • Zhiyuan Liu
  • 281 Publications • 17,656 Citations
  • J. Leskovec
  • 405 Publications • 85,399 Citations
  • Yoshua Bengio
  • 848 Publications • 361,613 Citations
  • Publications
  • Influence
Graph Neural Networks: A Review of Methods and Applications
View PDF on arXiv
Adaptive Graph Encoder for Attributed Graph Embedding
TLDR
Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on node clustering and link prediction tasks, and the proposed Adaptive Graph Encoder employs an adaptive encoder that iteratively strengthens the filtered features for better node embeddings.
View on ACM
Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks
TLDR
This paper proposes a novel multi-scale diffusion prediction model based on reinforcement learning (RL), which incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the non-differentiable problem.
View via Publisher
Machine-Learning-Driven Matrix Ordering for Power Grid Analysis
TLDR
A machine-learning-driven approach for matrix ordering is proposed for power grid analysis based on domain decomposition that achieves superior efficiency in runtime and memory usage over conventional methods, as demonstrated by industrial test cases.
View on IEEE
Full-Scale Information Diffusion Prediction With Reinforced Recurrent Networks.
TLDR
This article proposes a novel full-scale diffusion prediction model based on reinforcement learning (RL), which incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the nondifferentiable problem.
View on PubMed
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
TLDR
This paper explores the universal vulnerability of the prompt-based learning paradigm by injecting backdoor triggers or searching for adversarial triggers on pretrained language models using only plain text, and proposes a potential solution to mitigate the attack methods.
View PDF on arXiv
A Roadmap for Big Model
TLDR
This paper discusses not only the BM technologies themselves but also the prerequisites for BM training and applications with BMs, dividing the BM review into four parts: Resource, Models, Key Technologies and Application.
View PDF on arXiv
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks
TLDR
This work categorizes existing works into three practical scenarios in which attackers release datasets, pre-trained models, and fine-tuned models respectively, then discusses their unique evaluation methodologies, and proposes CUBE, a simple yet strong clustering-based defense baseline.
View PDF on arXiv
Capacitance Extraction and Power Grid Analysis Using Statistical and AI Methods
TLDR
The Markov-chain model and relevant analysis are presented for developing an efficient technique for handling conformal dielectrics in the floating random walk based capacitance extraction and two approaches reducing the computational cost of a domain decomposition based power-grid solver are presented.
View on IEEE
Evaluating Modules in Graph Contrastive Learning
TLDR
A set of module-level guidelines for GCL are proposed, e.g., simple samplers from LINE and DeepWalk are strong and robust; an MLP encoder associated with Sum readout could achieve competitive performance on graph classification.
View PDF on arXiv
...
...