Kai Zhang

Hotel recommendation based on user preference analysis

2015

Recommender system offers personalized suggestions by analyzing user preference. However, the performance falls sharply when it encounters sparse data, especially meets a cold start user. Hotel is such kind of goods that suffers a lot …

Leveraging Latent Sentiment Constraint in Probabilistic Matrix Factorization for Cross-domain Sentiment Classification

2016 · Procedia Computer Science

Sentiment analysis is concerned with classifying a subjective text into positive or negative according to the opinion expressed in it. The performance of traditional sentiment classification algorithms rely heavily on manually labeled training data. However, …

Discussion on private cloud PaaS construction of large scale enterprise

2016

In the process of enterprise information construction, the emergence of Cloud Computing is undoubtedly a huge revolution, which makes the enterprise more flexible to choose private cloud, public cloud or hybrid cloud deployment according to …

Scalable and Soundness Verifiable Outsourcing Computation in Marine Mobile Computing

2017 · Wireless Communications and Mobile Computing

Outsourcing computation with verifiability is a merging notion in cloud computing, which enables lightweight clients to outsource costly computation tasks to the cloud and efficiently check the correctness of the result in the end. This …

Interactive Attention Transfer Network for Cross-Domain Sentiment Classification

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

Cross-domain sentiment classification refers to utilizing useful knowledge in the source domain to help sentiment classification in the target domain which has few or no labeled data. Most existing methods mainly concentrate on extracting common …

Multipartite Quantum Entanglement and Quantum Correlation from cascaded Four-wave Mixing Processes with spatial multiplexing

2018 · Conference on Lasers and Electro-Optics

Four-wave mixing (FWM) process with spatial multiplexing is a promising candidate for building quantum network. We experimentally investigate multipartite quantum correlation and theoretically study multipartite quantum entanglement from cascaded FWM processes.

Query-Response Interactions by Multi-tasks in Semantic Search for Chatbot Candidate Retrieval

2022 · arXiv (Cornell University)

Semantic search for candidate retrieval is an important yet neglected problem in retrieval-based Chatbots, which aims to select a bunch of candidate responses efficiently from a large pool. The existing bottleneck is to ensure the …

Memory-adaptive Depth-wise Heterogeneous Federated Learning

2023 · arXiv (Cornell University)

Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT …

Large Language Model Instruction Following: A Survey of Progresses and Challenges

2023 · arXiv (Cornell University)

Task semantics can be expressed by a set of input-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of …

Unsupervised Abnormality Detection with Normalizing Flow and Neural Network

2023

In anomaly detection, the limited number of abnormal samples results in a significant long-tail distribution in the data. Additionally, labeling is heavily dependent on the experience and can be time-consuming. This problem is particularly prominent …

Finite-Time Controller Design for Continuous-Time T–S Fuzzy Systems With Partly Measurable Premise Variables

2024

The research presented in this paper delves into the finite-time control problem of Takagi-Sugeno (T-S) fuzzy systems with partly measurable premise variables. Firstly, through the application of the H∞analysis technique and the local stabilization analysis …

Personality Prediction for State Grid E-Learning Text Based on Neural Networks with Attention Mechanism

2024

State Grid Corporation of China (SGCC), as the leading enterprise in China’s power industry, is well aware that employees are the core strength of enterprise development, and therefore has always attached great importance to employee …

Dynamic Denoising of Contrastive Learning for GNN-based Node Embedding

2024

Contrastive learning is a powerful learning paradigm that can fully exploit cheap, self-supervised learning signals in the data. Crucial to its success is the choice of the positive and negative pairs, yet they are typically …

KA2SE: Key-Aggregation Authorized Searchable Encryption Scheme for Data Sharing in Wireless Sensor Networks

2024 · IEEE Transactions on Services Computing

As a promising technology, key-aggregation searchable encryption with constant computation overhead is especially suitable for sensor nodes with limited computation resources in wireless sensor networks. However, in most of the existing key-aggregation searchable encryption schemes, …

EP-CFG: Energy-Preserving Classifier-Free Guidance

2024 · arXiv (Cornell University)

Classifier-free guidance (CFG) is widely used in diffusion models but often\nintroduces over-contrast and over-saturation artifacts at higher guidance\nstrengths. We present EP-CFG (Energy-Preserving Classifier-Free Guidance),\nwhich addresses these issues by preserving the energy distribution of the\nconditional prediction …

Design of the Big Data Acquisition and Interlock Device for the RF System of Particle Accelerators

2024

Artificial intelligence (AI) technology is becoming a powerful tool for the control and optimization of particle accelerators, which is increasingly used in various accelerators. However, the efficacy of these AI algorithms relies on model training, …

Pattern Hiding and Authorized Searchable Encryption for Data Sharing in Cloud Storage

2025 · IEEE Transactions on Knowledge and Data Engineering

Secure cloud storage is a prevalent way to provide data retrieval services, where users’ data are encrypted before uploading to the cloud. To effectively perform keyword searches over the encrypted data, the approach of searchable …

An Efficient Bearing Prognostic Approach through Modeling Multiperiodic and Nonperiodic Temporal Patterns

2025 · IEEE Transactions on Industrial Informatics

Remaining useful life (RUL) prediction of bearings is essential for effective prognostics and health management (PHM). Although deep learning-based RUL prediction methods achieve high prediction accuracy, they often introduce significant parameter redundancy due to their …

Stepwise Reasoning Disruption Attack of LLMs

2025

Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

SimCDR: Preserving Intra-Domain Similarities of Users for Cross-Domain Recommendation

2025 · ACM Transactions on Information Systems

Cross-Domain Recommendation (CDR) can effectively alleviate the data sparsity issue in the recommendation system by transferring the source domain knowledge to the target domain. Many CDR methods try to find a mapping of latent embeddings …