Han Yu

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

2018 · arXiv (Cornell University)

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning. However, there …

Modulation recognition of composite modulation signal based on two-fold digital receiver and goodness of fit test

2021 · 2021 IEEE International Conference on Electronic Technology, Communication and Information (ICETCI)

Aiming at the modulation recognition problem of mixed signal set {BPSK, QPSK, BPSK-FM, QPSK-FM} with unknown parameters, this paper proposes a modulation recognition algorithm based on two-fold PLL (phase locked loop) and goodness of fit …

Automatic Product Copywriting for E-commerce

2022 · Proceedings of the AAAI Conference on Artificial Intelligence

Product copywriting is a critical component of e-commerce recommendation platforms. It aims to attract users' interest and improve user experience by highlighting product characteristics with textual descriptions. In this paper, we report our experience deploying …

FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learning

2022 · arXiv (Cornell University)

Large-scale neural networks possess considerable expressive power. They are well-suited for complex learning tasks in industrial applications. However, large-scale models pose significant challenges for training under the current Federated Learning (FL) paradigm. Existing approaches for …

Cultivation of Positive Psychological Quality of College Students' English Learning Under the Online and Offline Teaching Mode During the Epidemic

2022 · Frontiers in Public Health

During the COVID-19 pandemic, long-term isolation and loneliness will cause college students' psychological fluctuations. Especially in online teaching, the lack of communication for a long time has led to a greatly reduced learning enthusiasm of …

Towards Fairness-Aware Federated Learning

2021 · arXiv (Cornell University)

Recent advances in Federated Learning (FL) have brought large-scale collaborative machine learning opportunities for massively distributed clients with performance and data privacy guarantees. However, most current works focus on the interest of the central controller …

FL-Clip: Bridging Plasticity and Stability in Pre-Trained Federated Class-Incremental Learning Models

2024

Federated learning (FL) is the prevailing paradigm in privacy-preserving machine learning. Despite recent advances yielding state-of-the-art outcomes, FL systems face challenges in adapting to dynamic real-world scenarios, where the local data distributions of clients may …

Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learning

2024 · arXiv (Cornell University)

There is growing research interest in measuring the statistical heterogeneity of clients' local datasets. Such measurements are used to estimate the suitability for collaborative training of personalized federated learning (PFL) models. Currently, these research endeavors …

Efficient Threshold and Unbalanced Quorum PSI Protocols for Secure Data Sharing in Cloud-Assisted Internet of Things

2025 · IEEE Internet of Things Journal

Threshold private set intersection (t-PSI) protocol enables the secure determination of whether the intersection between two sets meets a specified threshold, facilitating privacy-preserving data collaboration in cloud computing for internet of things (IoT). However, existing …