Search Results for author: Qingyun Sun

Found 28 papers, 16 papers with code

MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery

no code implementations28 Feb 2024 Feihong Lu, Weiqi Wang, Yangyifei Luo, Ziqin Zhu, Qingyun Sun, Baixuan Xu, Haochen Shi, Shiqi Gao, Qian Li, Yangqiu Song, JianXin Li

However, understanding the intention behind social media posts remains challenging due to the implicitness of intentions in social media posts, the need for cross-modality understanding of both text and images, and the presence of noisy information such as hashtags, misspelled words, and complicated abbreviations.

Knowledge Distillation Language Modelling +2

Dynamic Graph Information Bottleneck

1 code implementation9 Feb 2024 Haonan Yuan, Qingyun Sun, Xingcheng Fu, Cheng Ji, JianXin Li

Leveraged by the Information Bottleneck (IB) principle, we first propose the expected optimal representations should satisfy the Minimal-Sufficient-Consensual (MSC) Condition.

Link Prediction Representation Learning

Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding

no code implementations19 Dec 2023 Yuecen Wei, Haonan Yuan, Xingcheng Fu, Qingyun Sun, Hao Peng, Xianxian Li, Chunming Hu

Specifically, PoinDP first learns the hierarchy weights for each entity based on the Poincar\'e model in hyperbolic space.

Graph Embedding Inductive Bias +3

Does Graph Distillation See Like Vision Dataset Counterpart?

2 code implementations NeurIPS 2023 Beining Yang, Kai Wang, Qingyun Sun, Cheng Ji, Xingcheng Fu, Hao Tang, Yang You, JianXin Li

We validate the proposed SGDD across 9 datasets and achieve state-of-the-art results on all of them: for example, on the YelpChi dataset, our approach maintains 98. 6% test accuracy of training on the original graph dataset with 1, 000 times saving on the scale of the graph.

Anomaly Detection Graph Representation Learning +1

Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification

1 code implementation11 Apr 2023 Xingcheng Fu, Yuecen Wei, Qingyun Sun, Haonan Yuan, Jia Wu, Hao Peng, JianXin Li

We find that training labeled nodes with different hierarchical properties have a significant impact on the node classification tasks and confirm it in our experiments.

Graph Representation Learning Node Classification

Unbiased and Efficient Self-Supervised Incremental Contrastive Learning

1 code implementation28 Jan 2023 Cheng Ji, JianXin Li, Hao Peng, Jia Wu, Xingcheng Fu, Qingyun Sun, Phillip S. Yu

Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning.

Contrastive Learning Graph Representation Learning +1

Self-organization Preserved Graph Structure Learning with Principle of Relevant Information

no code implementations30 Dec 2022 Qingyun Sun, JianXin Li, Beining Yang, Xingcheng Fu, Hao Peng, Philip S. Yu

Most Graph Neural Networks follow the message-passing paradigm, assuming the observed structure depicts the ground-truth node relationships.

Graph structure learning

Type Information Utilized Event Detection via Multi-Channel GNNs in Electrical Power Systems

no code implementations15 Nov 2022 Qian Li, JianXin Li, Lihong Wang, Cheng Ji, Yiming Hei, Jiawei Sheng, Qingyun Sun, Shan Xue, Pengtao Xie

To address the above issues, we propose a Multi-Channel graph neural network utilizing Type information for Event Detection in power systems, named MC-TED, leveraging a semantic channel and a topological channel to enrich information interaction from short texts.

Event Detection Semantic Similarity +2

Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation

1 code implementation2 Oct 2022 Yuecen Wei, Xingcheng Fu, Qingyun Sun, Hao Peng, Jia Wu, Jinyan Wang, Xianxian Li

To address this issue, we propose a novel heterogeneous graph neural network privacy-preserving method based on a differential privacy mechanism named HeteDP, which provides a double guarantee on graph features and topology.

Privacy Preserving

Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing

1 code implementation17 Aug 2022 Qingyun Sun, JianXin Li, Haonan Yuan, Xingcheng Fu, Hao Peng, Cheng Ji, Qian Li, Philip S. Yu

Topology-imbalance is a graph-specific imbalance problem caused by the uneven topology positions of labeled nodes, which significantly damages the performance of GNNs.

Graph Learning Graph structure learning +2

Automating DBSCAN via Deep Reinforcement Learning

2 code implementations9 Aug 2022 Ruitong Zhang, Hao Peng, Yingtong Dou, Jia Wu, Qingyun Sun, Jingyi Zhang, Philip S. Yu

DBSCAN is widely used in many scientific and engineering fields because of its simplicity and practicality.

Clustering Computational Efficiency +3

Curvature Graph Generative Adversarial Networks

1 code implementation3 Mar 2022 JianXin Li, Xingcheng Fu, Qingyun Sun, Cheng Ji, Jiajun Tan, Jia Wu, Hao Peng

In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named \textbf{\modelname}, which is the first GAN-based graph representation method in the Riemannian geometric manifold.

Generative Adversarial Network

Graph Structure Learning with Variational Information Bottleneck

1 code implementation16 Dec 2021 Qingyun Sun, JianXin Li, Hao Peng, Jia Wu, Xingcheng Fu, Cheng Ji, Philip S. Yu

Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications.

Graph structure learning

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network

1 code implementation15 Oct 2021 Xingcheng Fu, JianXin Li, Jia Wu, Qingyun Sun, Cheng Ji, Senzhang Wang, Jiajun Tan, Hao Peng, Philip S. Yu

Hyperbolic Graph Neural Networks(HGNNs) extend GNNs to hyperbolic space and thus are more effective to capture the hierarchical structures of graphs in node representation learning.

Graph Learning Multi-agent Reinforcement Learning +1

Convex Sparse Blind Deconvolution

no code implementations13 Jun 2021 Qingyun Sun, David Donoho

To bridge the gulf between reported successes and theory's limited understanding, we exhibit a convex optimization problem that -- assuming signal sparsity -- can convert a crude approximation to the true filter into a high-accuracy recovery of the true filter.

A Robust and Generalized Framework for Adversarial Graph Embedding

1 code implementation22 May 2021 JianXin Li, Xingcheng Fu, Hao Peng, Senzhang Wang, Shijie Zhu, Qingyun Sun, Philip S. Yu, Lifang He

With the prevalence of graph data in real-world applications, many methods have been proposed in recent years to learn high-quality graph embedding vectors various types of graphs.

Generative Adversarial Network Graph Embedding +4

A Recipe for Global Convergence Guarantee in Deep Neural Networks

no code implementations12 Apr 2021 Kenji Kawaguchi, Qingyun Sun

Existing global convergence guarantees of (stochastic) gradient descent do not apply to practical deep networks in the practical regime of deep learning beyond the neural tangent kernel (NTK) regime.

GRAC: Self-Guided and Self-Regularized Actor-Critic

1 code implementation18 Sep 2020 Lin Shao, Yifan You, Mengyuan Yan, Qingyun Sun, Jeannette Bohg

One dominant component of recent deep reinforcement learning algorithms is the target network which mitigates the divergence when learning the Q function.

Decision Making OpenAI Gym +2

Pairwise Learning for Name Disambiguation in Large-Scale Heterogeneous Academic Networks

no code implementations30 Aug 2020 Qingyun Sun, Hao Peng, Jian-Xin Li, Senzhang Wang, Xiangyu Dong, Liangxuan Zhao, Philip S. Yu, Lifang He

Although these attributes may change, an author's co-authors and research topics do not change frequently with time, which means that papers within a period have similar text and relation information in the academic network.

Attribute Graph Embedding

How to Close Sim-Real Gap? Transfer with Segmentation!

no code implementations14 May 2020 Mengyuan Yan, Qingyun Sun, Iuri Frosio, Stephen Tyree, Jan Kautz

Combining the control policy learned from simulation with the perception model, we achieve an impressive $\bf{88\%}$ success rate in grasping a tiny sphere with a real robot.

Robotics

Stochastic Modified Equations for Continuous Limit of Stochastic ADMM

no code implementations7 Mar 2020 Xiang Zhou, Huizhuo Yuan, Chris Junchi Li, Qingyun Sun

In this work, we put different variants of stochastic ADMM into a unified form, which includes standard, linearized and gradient-based ADMM with relaxation, and study their dynamics via a continuous-time model approach.

Degrees of Freedom Analysis of Unrolled Neural Networks

no code implementations10 Jun 2019 Morteza Mardani, Qingyun Sun, Vardan Papyan, Shreyas Vasanawala, John Pauly, David Donoho

Leveraging the Stein's Unbiased Risk Estimator (SURE), this paper analyzes the generalization risk with its bias and variance components for recurrent unrolled networks.

Image Restoration

A PID Controller Approach for Stochastic Optimization of Deep Networks

3 code implementations CVPR 2018 Wangpeng An, Haoqian Wang, Qingyun Sun, Jun Xu, Qionghai Dai, Lei Zhang

We first reveal the intrinsic connections between SGD-Momentum and PID based controller, then present the optimization algorithm which exploits the past, current, and change of gradients to update the network parameters.

Stochastic Optimization

Neural Proximal Gradient Descent for Compressive Imaging

1 code implementation NeurIPS 2018 Morteza Mardani, Qingyun Sun, Shreyas Vasawanala, Vardan Papyan, Hatef Monajemi, John Pauly, David Donoho

Recovering high-resolution images from limited sensory data typically leads to a serious ill-posed inverse problem, demanding inversion algorithms that effectively capture the prior information.

Bayesian Opponent Exploitation in Imperfect-Information Games

no code implementations10 Mar 2016 Sam Ganzfried, Qingyun Sun

The natural setting for opponent exploitation is the Bayesian setting where we have a prior model that is integrated with observations to create a posterior opponent model that we respond to.

Cannot find the paper you are looking for? You can Submit a new open access paper.