Qiang Yang

AutoCross

2019

Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses. In this paper, we present AutoCross, an automatic feature crossing tool provided by 4Paradigm to its …

Federated Learning in Mobile Edge Networks: A Comprehensive Survey

2019 · arXiv (Cornell University)

In recent years, mobile devices are equipped with increasingly advanced sensing and computing capabilities. Coupled with advancements in Deep Learning (DL), this opens up countless possibilities for meaningful applications. Traditional cloudbased Machine Learning (ML) approaches …

Posture Recognition Based on the Improved Optical Diffractive Neural Network

2020

Optical computing has significant advantages in power consumption efficiency and computing speed. As an optical machine learning framework, diffractive optical neural networks have achieved good results in the application of feature detection and target classification. …

Hierarchical Attention Transfer Network for Cross-Domain Sentiment Classification

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Cross-domain sentiment classification aims to leverage useful information in a source domain to help do sentiment classification in a target domain that has no or little supervised information. Existing cross-domain sentiment classification methods cannot automatically …

Federated Singular Vector Decomposition.

2021

With the promulgation of data protection laws (e.g., GDPR in 2018), privacy preservation has become a general agreement in applications where cross-domain sensitive data are utilized. Out of many privacy-preserving techniques, federated learning (FL) has …

No Free Lunch Theorem for Security and Utility in Federated Learning

2022 · ACM Transactions on Intelligent Systems and Technology

In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms. On one hand, private and sensitive training data …

Trading Off Privacy, Utility and Efficiency in Federated Learning

2022 · arXiv (Cornell University)

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in preserving \textit{privacy} …

A random elite ensemble learning swarm optimizer for high-dimensional optimization

2023 · Complex & Intelligent Systems

Abstract High-dimensional optimization problems are increasingly pervasive in real-world applications nowadays and become harder and harder to optimize due to increasingly interacting variables. To tackle such problems effectively, this paper designs a random elite ensemble …

A Unified Framework for Unsupervised Domain Adaptation based on Instance Weighting

2023 · arXiv (Cornell University)

Despite the progress made in domain adaptation, solving Unsupervised Domain Adaptation (UDA) problems with a general method under complex conditions caused by label shifts between domains remains a formidable task. In this work, we comprehensively …

Adaptive Crossover Selection for Differential Evolution to Solve Global Optimization Problems

2024

In response to the escalating demand for optimal solutions to intricate optimization problems in real world applications, differential evolution (DE) algorithms have shown very promising performance. However, most of existing DE studies leverage only one …

Population-Level Hybridization between Roulette Wheel Selection and Tournament Selection for Particle Swarm Optimization

2024

This paper introduces a population-level hybrid selection framework that combines the roulette wheel selection (RWS) and the tournament selection (TS) to pick promising exemplars to update particles, so as to ameliorate the capability of particle …

Individual-Level Dominant Exemplar Selection for Particle Swarm Optimization

2024

Leading exemplars play significant roles in updating particles to seek optimal solutions for Particle Swarm Optimization (PSO). Along this road, this paper devises an Individual-level Dominant Exemplar Selection (IDES) framework for PSO, giving rise to …

Flexible End-to-End Dialogue System for Knowledge Grounded Conversation

2017 · arXiv (Cornell University)

In knowledge grounded conversation, domain knowledge plays an important role in a special domain such as Music. The response of knowledge grounded conversation might contain multiple answer entities or no entity at all. Although existing …

CoNet

2018

The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In …

A Survey on Evaluation of Large Language Models

2024 · ACM Transactions on Intelligent Systems and Technology

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, …