Publications (41)
Importance of Small Probability Events in Big Data: Information Measures, Applications, and Challenges
Rui She, Shanyun Liu, Shuo Wan +2
In many applications (e.g., anomaly detection and security systems) of smart cities, rare events dominate the importance of the total information of big data collected by Internet…
Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach
Kai Zhao, Qiyu Kang, Yang Song +3
Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those that affect both node features and graph topology. This paper investigates GNNs derived fr…
CodeBoost: Boosting Code LLMs by Squeezing Knowledge from Code Snippets with RL
Sijie Wang, Quanjiang Guo, Kai Zhao +7
Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines. Existing models are typically post-trained using reinforcem…
LAMP: a micro-satellite based soft X-ray polarimeter for astrophysics
Rui She, Hua Feng, Fabio Muleri +19
The Lightweight Asymmetry and Magnetism Probe (LAMP) is a micro-satellite mission concept dedicated for astronomical X-ray polarimetry and is currently under early phase study. It…
UAVScenes: A Multi-Modal Dataset for UAVs
Sijie Wang, Siqi Li, Yawei Zhang +16
Multi-modal perception is essential for unmanned aerial vehicle (UAV) operations, as it enables a comprehensive understanding of the UAVs' surrounding environment. However, most ex…
Image Patch-Matching with Graph-Based Learning in Street Scenes
Rui She, Qiyu Kang, Sijie Wang +4
Matching landmark patches from a real-time image captured by an on-vehicle camera with landmark patches in an image database plays an important role in various computer perception…
Matching Users' Preference Under Target Revenue Constraints in Optimal Data Recommendation Systems
Shanyun Liu, Yunquan Dong, Pingyi Fan +2
This paper focuses on the problem of finding a particular data recommendation strategy based on the user preferences and a system expected revenue. To this end, we formulate this p…
Amplifying Inter-message Distance: On Information Divergence Measures in Big Data
Rui She, Shanyun Liu, Pingyi Fan
Message identification (M-I) divergence is an important measure of the information distance between probability distributions, similar to Kullback-Leibler (K-L) and Renyi divergenc…
DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition
Sijie Wang, Rui She, Qiyu Kang +4
The utilization of multi-modal sensor data in visual place recognition (VPR) has demonstrated enhanced performance compared to single-modal counterparts. Nonetheless, integrating a…
From MIM-Based GAN to Anomaly Detection:Event Probability Influence on Generative Adversarial Networks
Rui She, Pingyi Fan
In order to introduce deep learning technologies into anomaly detection, Generative Adversarial Networks (GANs) are considered as important roles in the algorithm design and realis…
How Many Samples Required in Big Data Collection: A Differential Message Importance Measure
Shanyun Liu, Rui She, Pingyi Fan
Information collection is a fundamental problem in big data, where the size of sampling sets plays a very important role. This work considers the information collection process by…
PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
Rui She, Qiyu Kang, Sijie Wang +7
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challe…
AgentDNS: A Root Domain Naming System for LLM Agents
Enfang Cui, Yujun Cheng, Rui She +7
The rapid evolution of Large Language Model (LLM) agents has highlighted critical challenges in cross-vendor service discovery, interoperability, and communication. Existing protoc…
Location-Adaptive Change-Point Testing for Time Series
Linlin Dai, Rui She
We propose a location-adaptive self-normalization (SN) based test for change points in time series. The SN technique has been extensively used in change-point detection for its cap…
Focusing on a Probability Element: Parameter Selection of Message Importance Measure in Big Data
Rui She, Shanyun Liu, Yunquan Dong +1
Message importance measure (MIM) is applicable to characterize the importance of information in the scenario of big data, similar to entropy in information theory. In fact, MIM wit…
Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study
Qiyu Kang, Kai Zhao, Yang Song +5
In this work, we rigorously investigate the robustness of graph neural fractional-order differential equation (FDE) models. This framework extends beyond traditional graph neural (…
Chandra Survey of Nearby Galaxies: A Significant Population of Candidate Central Black Holes in Late-type Galaxies
Rui She, Luis C. Ho, Hua Feng
Based on the Chandra data archive as of March 2016, we have identified 314 candidate active galactic nuclei in 719 galaxies located closer than 50 Mpc, among them late-type (Hubble…
HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
Sijie Wang, Qiyu Kang, Rui She +4
LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision. LiDAR-based retrieval from a database typically incurs high c…
An Importance Aware Weighted Coding Theorem Using Message Importance Measure
Zheqi Zhu, Shanyun Liu, Rui She +3
There are numerous scenarios in source coding where not only the code length but the importance of each value should also be taken into account. Different from the traditional codi…
A2H: Agent-to-Human Protocol for AI Agent
Zhiyuan Liang, Enfang Cui, Qian Wei +4
AI agents are increasingly deployed as autonomous systems capable of planning, tool use, and multi-agent collaboration across complex tasks. However, existing agent-related protoco…
Non-parametric Message Important Measure: Storage Code Design and Transmission Planning for Big Data
Shanyun Liu, Rui She, Pingyi Fan +1
Storage and transmission in big data are discussed in this paper, where message importance is taken into account. Similar to Shannon Entropy and Renyi Entropy, we define non-parame…
Differential Message Importance Measure: A New Approach to the Required Sampling Number in Big Data Structure Characterization
Shanyun Liu, Rui She, Pingyi Fan
Data collection is a fundamental problem in the scenario of big data, where the size of sampling sets plays a very important role, especially in the characterization of data struct…
Information Measure Similarity Theory: Message Importance Measure via Shannon Entropy
Rui She, Shanyun Liu, Pingyi Fan
Rare events attract more attention and interests in many scenarios of big data such as anomaly detection and security systems. To characterize the rare events importance from proba…
PRFusion: Toward Effective and Robust Multi-Modal Place Recognition with Image and Point Cloud Fusion
Sijie Wang, Qiyu Kang, Rui She +3
Place recognition plays a crucial role in the fields of robotics and computer vision, finding applications in areas such as autonomous driving, mapping, and localization. Place rec…
A Switch to the Concern of User: Importance Coefficient in Utility Distribution and Message Importance Measure
Shanyun Liu, Rui She, Shuo Wan +2
This paper mainly focuses on the utilization frequency in receiving end of communication systems, which shows the inclination of the user about different symbols. When the average…
Chandra Survey of Nearby Galaxies: The Catalog
Rui She, Luis C. Ho, Hua Feng
We searched in the public archive of the Chandra X-ray Observatory as of March 2016 and assembled a sample of 719 galaxies within 50 Mpc with ACIS observations available. By cross-…
State Variation Mining: On Information Divergence with Message Importance in Big Data
Rui She, Shanyun Liu, Pingyi Fan
Information transfer which reveals the state variation of variables usually plays a vital role in big data analytics and processing. In fact, the measures for information transfer…
Graph Neural Convection-Diffusion with Heterophily
Kai Zhao, Qiyu Kang, Yang Song +3
Graph neural networks (GNNs) have shown promising results across various graph learning tasks, but they often assume homophily, which can result in poor performance on heterophilic…
Storage Space Allocation Strategy for Digital Data with Message Importance
Shanyun Liu, Rui She, Zheqi Zhu +1
This paper mainly focuses on the problem of lossy compression storage from the perspective of message importance when the reconstructed data pursues the least distortion within lim…
A Two-step Estimating Approach for Heavy-tailed AR Models with Non-zero Median GARCH-type Noises
Rui She, Linlin Dai, Shiqing Ling
This paper develops a novel two-step estimating procedure for heavy-tailed AR models with non-zero median GARCH-type noises, allowing for time-varying volatility. We first establis…
Chandra Survey of Nearby Galaxies: Testing the Accretion Model for Low-luminosity AGNs
Rui She, Luis C. Ho, Hua Feng +1
From a Chandra sample of active galactic nuclei (AGNs) in nearby galaxies, we find that for low-luminosity AGNs (LLAGNs), either the intrinsic absorption column density, or the fra…
Building Facade Parsing R-CNN
Sijie Wang, Qiyu Kang, Rui She +3
Building facade parsing, which predicts pixel-level labels for building facades, has applications in computer vision perception for autonomous vehicle (AV) driving. However, instea…
RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challenging Environments
Rui She, Qiyu Kang, Sijie Wang +4
For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing. In various computer percepti…
RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments
Sijie Wang, Qiyu Kang, Rui She +3
Camera relocalization has various applications in autonomous driving. Previous camera pose regression models consider only ideal scenarios where there is little environmental pertu…
Learning Channel Capacity with Neural Mutual Information Estimator Based on Message Importance Measure
Zhefan Li, Rui She, Pingyi Fan +2
Channel capacity estimation plays a crucial role in beyond 5G intelligent communications. Despite its significance, this task is challenging for a majority of channels, especially…
Node Embedding from Hamiltonian Information Propagation in Graph Neural Networks
Qiyu Kang, Kai Zhao, Yang Song +3
Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data. However, common challenges faced by many GNNs in the literature include the…
MIM-Based GAN: Information Metric to Amplify Small Probability Events Importance in Generative Adversarial Networks
Rui She, Pingyi Fan
In terms of Generative Adversarial Networks (GANs), the information metric to discriminate the generative data from the real data, lies in the key point of generation efficiency, w…
PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations
Rui She, Sijie Wang, Qiyu Kang +5
Point cloud registration is a crucial technique in 3D computer vision with a wide range of applications. However, this task can be challenging, particularly in large fields of view…
Personalized Subgraph Federated Learning with Sheaf Collaboration
Wenfei Liang, Yanan Zhao, Rui She +2
Graph-structured data is prevalent in many applications. In subgraph federated learning (FL), this data is distributed across clients, each with a local subgraph. Personalized subg…
FedSheafHN: Personalized Federated Learning on Graph-structured Data
Wenfei Liang, Yanan Zhao, Rui She +2
Personalized subgraph Federated Learning (FL) is a task that customizes Graph Neural Networks (GNNs) to individual client needs, accommodating diverse data distributions. However,…
Shannon Shakes Hands with Chernoff: Big Data Viewpoint On Channel Information Measures
Shanyun Liu, Rui She, Jiaxun Lu +1
Shannon entropy is the most crucial foundation of Information Theory, which has been proven to be effective in many fields such as communications. Renyi entropy and Chernoff inform…