Author name cluster

Hanchao Yu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

IJCAI Conference 2024 Conference Paper

FedES: Federated Early-Stopping for Hindering Memorizing Heterogeneous Label Noise

Bixiao Zeng
Xiaodong Yang
Yiqiang Chen
Zhiqi Shen
Hanchao Yu
Yingwei Zhang

Federated learning (FL) facilitates collaborative model training across distributed clients while maintaining privacy. Federated noisy label learning (FNLL) is more of a challenge for data inaccessibility and noise heterogeneity. Existing works primarily assume clients are either noisy or clean, which may lack the flexibility to adapt to diverse label noise across different clients, especially when entirely clean or noisy clients are not the majority. To address this, we propose a general noise-robust federated learning framework called Federated Early-Stopping (FedES), which adaptively updates critical parameters of each local model based on their noise rates, thereby avoiding overfitting to noisy labels. FedES is composed of two stages: federated noise estimation and parameter-adaptive local updating \& global aggregation. We introduce a signed distance based on local and global gradients during a federated round to estimate clients' noise rates without requiring additional information. Based on this measure, we employ various degrees of early-stopping during local updating on the clients, and further, a noise-aware global aggregation is employed to achieve noise-robust learning. Extensive experiments conducted on varying synthetic and real-world label noise demonstrate the superior performance of FedES over the state-of-the-art methods.

PDF Details DOI

TIST Journal 2022 Journal Article

CLC: A Consensus-based Label Correction Approach in Federated Learning

Bixiao Zeng
Xiaodong Yang
Yiqiang Chen
Hanchao Yu
Yingwei Zhang

Federated learning (FL) is a novel distributed learning framework where multiple participants collaboratively train a global model without sharing any raw data to preserve privacy. However, data quality may vary among the participants, the most typical of which is label noise. The incorrect label would significantly damage the performance of the global model. In FL, the inaccessibility of raw data makes this issue more challenging. Previously published studies are limited to using a task-specific benchmark-trained model to evaluate the relevance between the benchmark dataset in the server and the local one on the participants’ side. However, such approaches have failed to exploit the cooperative nature of FL itself and are not practical. This paper proposes a Consensus-based Label Correction approach (CLC) in FL, which tries to correct the noisy labels using the developed consensus method among the FL participants. The consensus-defined class-wise information is used to identify the noisy labels and correct them with pseudo-labels. Extensive experiments are conducted on several public datasets in various settings. The experimental results prove the advantage over the state-of-art methods. The link to the source code is https://github.com/bixiao-zeng/CLC.git.

Details DOI

IJCAI Conference 2020 Conference Paper

Bridging Cross-Tasks Gap for Cognitive Assessment via Fine-Grained Domain Adaptation

Yingwei Zhang
Yiqiang Chen
Hanchao Yu
Zeping Lv
Qing Li
Xiaodong Yang

Discriminating pathologic cognitive decline from the expected decline of normal aging is an important research topic for elderly care and health monitoring. However, most cognitive assessment methods only work when data distributions of the training set and testing set are consistent. Enabling existing cognitive assessment models to adapt to the data in new cognitive assessment tasks is a significant challenge. In this paper, we propose a novel domain adaptation method, namely the Fine-Grained Adaptation Random Forest (FAT), to bridge the cognitive assessment gap when the data distribution is changed. FAT is composed of two essential parts 1) information gain based model evaluation strategy (IGME) and 2) domain adaptation tree growing mechanism (DATG). IGME is used to evaluate every individual tree, and DATG is used to transfer the source model to the target domain. To evaluate the performance of FAT, we conduct experiments in real clinical environments. Experimental results demonstrate that FAT is significantly more accurate and efficient compared with other state-of-the-art methods.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Instance-Wise Dynamic Sensor Selection for Human Activity Recognition

Xiaodong Yang
Yiqiang Chen
Hanchao Yu
Yingwei Zhang
Wang Lu
Ruizhe Sun

Human Activity Recognition (HAR) is an important application of smart wearable/mobile systems for many humancentric problems such as healthcare. The multi-sensor synchronous measurement has shown better performance for HAR than a single sensor. However, the multi-sensor setting increases the costs of data transmission, computation and energy. Therefore, the efﬁcient sensor selection to balance recognition accuracy and sensor cost is the critical challenge. In this paper, we propose an Instance-wise Dynamic Sensor Selection (IDSS) method for HAR. Firstly, we formalize this problem as minimizing both activity classiﬁcation loss and sensor number by dynamically selecting a sparse subset for each instance. Then, IDSS solves the above minimization problem via Markov Decision Process whose policy for sensor selection is learned by exploiting the instancewise states using Imitation Learning. In order to optimize the parameters of the activity classiﬁcation model and the sensor selection policy, an algorithm named Mutual DAgger is proposed to alternatively enhance their learning process. To evaluate the performance of IDSS, we conduct experiments on three real-world HAR datasets. The experimental results show that IDSS can effectively reduce the overall sensor number without losing accuracy and outperforms the state-of-theart methods regarding the combined measurement of accuracy and sensor number.

PDF Details

IS Journal 2013 Journal Article

Extreme Learning Machines [Trends & Controversies]

Erik Cambria
Guang-Bin Huang
Liyanaarachchi Lekamalage Chamara Kasun
Hongming Zhou
Chi Man Vong
Jiarun Lin
Jianping Yin
Zhiping Cai

This special issue includes eight original works that detail the further developments of ELMs in theories, applications, and hardware implementation. In "Representational Learning with ELMs for Big Data, " Liyanaarachchi Lekamalage Chamara Kasun, Hongming Zhou, Guang-Bin Huang, and Chi Man Vong propose using the ELM as an auto-encoder for learning feature representations using singular values. In "A Secure and Practical Mechanism for Outsourcing ELMs in Cloud Computing, " Jiarun Lin, Jianping Yin, Zhiping Cai, Qiang Liu, Kuan Li, and Victor C. M. Leung propose a method for handling large data applications by outsourcing to the cloud that would dramatically reduce ELM training time. In "ELM-Guided Memetic Computation for Vehicle Routing, " Liang Feng, Yew-Soon Ong, and Meng-Hiot Lim consider the ELM as an engine for automating the encapsulation of knowledge memes from past problem-solving experiences. In "ELMVIS: A Nonlinear Visualization Technique Using Random Permutations and ELMs, " Anton Akusok, Amaury Lendasse, Rui Nian, and Yoan Miche propose an ELM method for data visualization based on random permutations to map original data and their corresponding visualization points. In "Combining ELMs with Random Projections, " Paolo Gastaldo, Rodolfo Zunino, Erik Cambria, and Sergio Decherchi analyze the relationships between ELM feature-mapping schemas and the paradigm of random projections. In "Reduced ELMs for Causal Relation Extraction from Unstructured Text, " Xuefeng Yang and Kezhi Mao propose combining ELMs with neuron selection to optimize the neural network architecture and improve the ELM ensemble's computational efficiency. In "A System for Signature Verification Based on Horizontal and Vertical Components in Hand Gestures, " Beom-Seok Oh, Jehyoung Jeon, Kar-Ann Toh, Andrew Beng Jin Teoh, and Jaihie Kim propose a novel paradigm for hand signature biometry for touchless applications without the need for handheld devices. Finally, in "An Adaptive and Iterative Online Sequential ELM-Based Multi-Degree-of-Freedom Gesture Recognition System, " Hanchao Yu, Yiqiang Chen, Junfa Liu, and Guang-Bin Huang propose an online sequential ELM-based efficient gesture recognition algorithm for touchless human-machine interaction.

Details DOI