Yang Xu

Analysis of Web Access Sequence Based on the Improved Prefix Span Algorithm

2015 · Advances in computer science research

PrefixSpan is an important algorithm for sequential pattern mining algorithm, but it's projected database cost more redundant memory and scan-time, so this paper present an improved PrefixSpan algorithm(IPS) which is based on PrefixSpan. IPS decreases …

Knowledge-oriented semantics modelling towards uncertainty reasoning

2016 · SpringerPlus

Distributed reasoning in M2M leverages the expressive power of ontology to enable semantic interoperability between heterogeneous systems of connected devices. Ontology, however, lacks the built-in, principled support to effectively handle the uncertainty inherent in M2M …

QoS-Based Service Selection Method for Big Data Service Composition

2017

Different from the traditional web services, the big data services' execution duration vary from the input data volume, so the traditional Quality of Service (QoS) analysis model for traditional web services cannot be directly applied …

Set-Blocked Clause and Extended Set-Blocked Clause in First-Order Logic

2018 · Symmetry

Due to scale and complexity of first-order formulas, simplifications play a very important role in first-order theorem proving, in which removal of clauses and literals identified as redundant is a significant component. In this paper, …

Word class flexibility: A deep contextualized approach

2020 · arXiv (Cornell University)

Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories. Extensive work in linguistic typology has sought to characterize word class flexibility across languages, but quantifying this …

Identifying Mis-Configured Author Profiles on Google Scholar Using Deep Learning

2021 · Applied Sciences

Google Scholar has been a widely used platform for academic performance evaluation and citation analysis. The issue about the mis-configuration of author profiles may seriously damage the reliability of the data, and thus affect the …

Enhancing Federated Learning with In-Cloud Unlabeled Data

2022 · 2022 IEEE 38th International Conference on Data Engineering (ICDE)

Federated learning (FL) has been widely applied to collaboratively train deep learning (DL) models on massive end devices (i.e., clients). Due to the limited storage capacity and high labeling cost, there are always insufficient data …

Neural reality of argument structure constructions

2022 · arXiv (Cornell University)

In lexicalist linguistic theories, argument structure is assumed to be predictable from the meaning of verbs. As a result, the verb is the primary determinant of the meaning of a clause. In contrast, construction grammarians …

Automated Hyperparameter Optimization of Gradient Boosting Decision Tree Approach for Gold Mineral Prospectivity Mapping in the Xiong’ershan Area

2022 · Minerals

The weak classifier ensemble algorithms based on the decision tree model, mainly include bagging (e.g., fandom forest-RF) and boosting (e.g., gradient boosting decision tree, eXtreme gradient boosting), the former reduces the variance for the overall …

Adaptive Block-Wise Regularization and Knowledge Distillation for Enhancing Federated Learning

2023 · IEEE/ACM Transactions on Networking

Federated Learning (FL) is a distributed model training framework that allows multiple clients to collaborate on training a global model without disclosing their local data in edge computing (EC) environments. However, FL usually faces statistical …

FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling

2024 · arXiv (Cornell University)

In recent years, Cross-Domain Recommendation (CDR) has drawn significant attention, which utilizes user data from multiple domains to enhance the recommendation performance. However, current CDR methods require sharing user data across domains, thereby violating the …

FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learning

2024 · Society for Industrial and Applied Mathematics eBooks

Cross-domain Sequential Recommendation (CSR) which leverages user sequence data from multiple domains has received extensive attention in recent years. However, the existing CSR methods require sharing origin user data across domains, which violates the General …

Concise and Precise Context Compression for Tool-Using Language Models

2024

Yang Xu, Yunlong Feng, Honglin Mu, Yutai Hou, Yitong Li, Xinghao Wang, Wanjun Zhong, Zhongyang Li, Dandan Tu, Qingfu Zhu, Min Zhang, Wanxiang Che. Findings of the Association for Computational Linguistics: ACL 2024. 2024.

Collaborative Speculative Inference for Efficient LLM Inference Serving

2025 · arXiv (Cornell University)

Speculative inference is a promising paradigm employing small speculative models (SSMs) as drafters to generate draft tokens, which are subsequently verified in parallel by the target large language model (LLM). This approach enhances the efficiency …

Deeply Fusing Reviews and Contents for Cold Start Users in Cross-Domain Recommendation Systems

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

As one promising way to solve the challenging issues of data sparsity and cold start in recommender systems, crossdomain recommendation has gained increasing research interest recently. Cross-domain recommendation aims to improve the recommendation performance by …