Jun Zhou

Satellite Telemetry Data Anomaly Detection with Hybrid Similarity Measures

2017 · 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)

Anomaly detection based on telemetry data can improve the operating safety for spacecrafts. Most of the anomaly detection methods in this domain are based on Euclidean distance for similarity measure of monitoring parameters. However, the …

Feature Propagation on Graph: A New Perspective to Graph Representation Learning

2018 · arXiv (Cornell University)

We study feature propagation on graph, an inference process involved in graph representation learning tasks. It's to spread the features over the whole graph to the $t$-th orders, thus to expand the end's features. The …

Distributed Deep Forest and its Application to Automatic Detection of Cash-out Fraud

2018 · arXiv (Cornell University)

Internet companies are facing the need for handling large-scale machine learning applications on a daily basis and distributed implementation of machine learning algorithms which can handle extra-large scale tasks with great performance is widely needed. …

Ensemble based on Constraint Projection and Under-Sampling for Imbalanced Learning

2018

Ensemble method is widely used in imbalanced learning, and it is well known that diverse and accurate base classifiers are the keys to the success of an ensemble. This paper proposes a novel ensemble method …

Intuitionistic Fuzzy Dynamic Bayesian Network and its Application to Terminating Situation Assessment

2019 · Procedia Computer Science

The period of terminating situation in air combat is time-varying and full of information with uncertainty. In order to process the fuzzy information in time series and assess the situation effectively, Intuitionistic Fuzzy Dynamic Bayesian …

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing

2019

Mobile payment such as Alipay has been widely used in our daily lives. To further promote the mobile payment activities, it is important to run marketing campaigns under a limited budget by providing incentives such …

Privacy Preserving PCA for Multiparty Modeling

2020 · arXiv (Cornell University)

In this paper, we present a general multiparty modeling paradigm with Privacy Preserving Principal Component Analysis (PPPCA) for horizontally partitioned data. PPPCA can accomplish multiparty cooperative execution of PCA under the premise of keeping plaintext …

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing

2020 · arXiv (Cornell University)

Mobile payment such as Alipay has been widely used in our daily lives. To further promote the mobile payment activities, it is important to run marketing campaigns under a limited budget by providing incentives such …

Counterfactual Review-based Recommendation

2021

Incorporating review information into the recommender system has been demonstrated to be an effective method for boosting the recommendation performance. Previous research mainly focus on designing advanced architectures to better profile the users and items. …

SIMGAT: A Sentiment Analysis Model Based on Graph Attention Mechanism

2022

With the normalization of social media, the popularization of Chinese, how to effectively enable computers to recognize Chinese short-text messages is an important task for network public opinion management and control. Due to the complexity …

Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design

2020 · arXiv (Cornell University)

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build privacy preserving DNN models …

QCA-Net: Quantum-based Channel Attention for Deep Neural Networks

2023

The channel attention mechanism, which adaptively recalibrates each channel's weight, can enhance the performance of deep neural networks. Most channel attention modules use simple pooling operations to aggregate spatial information. The drawback is the incapability …

GLISP: A Scalable GNN Learning System by Exploiting Inherent Structural Properties of Graphs

2024 · arXiv (Cornell University)

As a powerful tool for modeling graph data, Graph Neural Networks (GNNs) have received increasing attention in both academia and industry. Nevertheless, it is notoriously difficult to deploy GNNs on industrial scale graphs, due to …

Can Small Language Models be Good Reasoners for Sequential Recommendation?

2024 · arXiv (Cornell University)

Large language models (LLMs) open up new horizons for sequential recommendations, owing to their remarkable language comprehension and generation capabilities. However, there are still numerous challenges that should be addressed to successfully implement sequential recommendations …

Linkable, <i>k</i>-Times Traceable, and Revocable Ring Signature for Fine-Grained Accountability in Blockchain Transactions

2024 · IEEE Internet of Things Journal

Ring signatures are a useful cryptographic technique for anonymous transactions on the blockchain, which allows a user to sign a message on behalf of a group, without revealing which specific member of the group did …

From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence

2025 · arXiv (Cornell University)

Uncertainty quantification (UQ) is a critical aspect of artificial intelligence (AI) systems, particularly in high-risk domains such as healthcare, autonomous systems, and financial technology, where decision-making processes must account for uncertainty. This review explores the …

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

2025 · arXiv (Cornell University)

High-quality, large-scale instructions are crucial for aligning large language models (LLMs), however, there is a severe shortage of instruction in the field of natural language understanding (NLU). Previous works on constructing NLU instructions mainly focus …

External Knowledge Is Not Always Needed: An Adaptive Retrieval Augmented Generation Method

2024

Retrieval augmented generation (RAG), by integrating external knowledge with large language models (LLMs), has become a common practice to alleviate LLMs’ hallucination problem. The performance of RAG, however, depends on the capability of the adopted …

Making Large Vision Language Models to Be Good Few-Shot Learners

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

Few-shot classification (FSC) is a fundamental yet challenging task in computer vision that involves recognizing novel classes from limited data. While previous methods have focused on enhancing visual features or incorporating additional modalities, Large Vision …

On learning denoisable student logits

2026 · Pattern Recognition

Knowledge Distillation (KD) aims to train a student model to mimic the behavior of a more powerful teacher model. In this paper, we reveal that through the lens of diffusion processes, student logits can be …

cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

We propose cw2vec, a novel method for learning Chinese word embeddings. It is based on our observation that exploiting stroke-level information is crucial for improving the learning of Chinese word embeddings. Specifically, we design a …

Privacy Preserving Point-of-Interest Recommendation Using Decentralized Matrix Factorization

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Points of interest (POI) recommendation has been drawn much attention recently due to the increasing popularity of location-based networks, e.g., Foursquare and Yelp. Among the existing approaches to POI recommendation, Matrix Factorization (MF) based techniques …

Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction

2021

In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest in the recent literature. However, despite being extensively studied, these sequential methods still suffer from three limitations. …

Cross-Domain Recommendation: Challenges, Progress, and Prospects

2021

To address the long-standing data sparsity problem in recommender systems (RSs), cross-domain recommendation (CDR) has been proposed to leverage the relatively richer information from a richer domain to improve the recommendation performance in a sparser …