Author name cluster

Ziyi Li

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.

6 papers

1 author row

EAAI Journal 2025 Journal Article

Adaptive Deformable Convolutional Neural Network Framework for depression-related behavioral analysis in mice

Jian Li
Ziyi Li
Peng Shan
Xiaoyong Lyu
Yu Tian
Chen Du
Ying Wang
Yuliang Zhao

The use of approximately 1 billion laboratory animals annually in research highlights the urgent need for advanced methods to analyze behavioral dynamics, particularly in mice. Capturing subtle and prolonged behavioral changes, such as those observed in long-term depression studies, poses a significant challenge. To address this, we propose an Adaptive Deformable Convolutional Neural Network Framework for depression-related behavioral analysis in mice. By integrating DeepLabCut (DLC) with deformable convolutional networks (DCN) and convolutional block attention module (CBAM), the framework captures subtle and prolonged behavioral changes with high precision. Adaptive image deformation encodes joint movements into image representations, enabling robust analysis of spatial and temporal patterns. In depression modeling experiment, the framework achieved over 80% classification accuracy, demonstrating its scalability and efficiency. This non-invasive, automated solution represents a transformative advancement in behavioral analysis, offering a reliable tool for long-term studies in animal models.

Details DOI

YNIMG Journal 2025 Journal Article

Dynamic reconfiguration of default and frontoparietal network supports creative incubation

Ziyi Li
Ze Zhang
Tengteng Tan
Jing Luo

Although creative ideas often emerge during distraction activities unrelated to the creative task, empirical research has yet to reveal the underlying neurocognitive mechanism. Using an incubation paradigm, we temporarily disengaged participants from the initial creative ideation task and required them to conduct two different distraction activities (moderately-demanding: 1-back working memory task, non-demanding: 0-back choice reaction time task), then returned them to the previous creative task. On the process of creative ideation, we calculated the representational dissimilarities between the two creative ideation phases before and after incubation period to estimate the neural representational change underlying successful incubation. The results found that, for the 0-back condition, successful incubation was associated with the representational change in precuneus (PCU), whereas for the 1-back condition, it was associated with change in rostrolateral PFC (rlPFC), suggesting the dual processes of the DMN-mediated associative thinking and PFC-mediated controlled thinking for the 0- or the 1-back incubation conditions to prompt creation. On the incubation delay, we found the successful incubation in both conditions was accompanied with network integration between frontoparietal (FP) and default mode (DM) network, further suggesting the coupling of the controlled- and associative-thinking for the incubation to work. Moreover, we found the FP-DM integration during incubation period could respectively predict the representational change in PCU or rlPFC in the creative ideation phase of 0- or 1-back condition. This means both conditions benefits from the coordination of the controlled and of the associative thinking in incubation period, but for the representational change in creative ideation phase, 1-back condition relies more on the controlled thinking, whereas the 0-back on the associative ones. Additionally, we created a neural encoding indicator to assess the degree to which temporal activities in the rlPFC or PCU during incubation delay is related to the after-incubation successful problem-solving, and we found a positive relation between this indicator and dynamic reconfiguration of brain networks. This further indicates that FP-DM integration supports creative incubation through offline processing.

Details DOI

AAAI Conference 2025 Conference Paper

HaCore: Efficient Coreset Construction with Locality Sensitive Hashing for Vertical Federated Learning

Qinbo Zhang
Xiao Yan
Yukai Ding
Fangcheng Fu
Quanqing Xu
Ziyi Li
Chuang Hu
Jiawei Jiang

Vertical federated learning (VFL) trains model when the features of data samples are scattered over multiple clients. To improve efficiency, a promising approach is to find a coreset of the data samples and use it as a smaller training set. However, existing methods produce a large coreset when there are many clients and have long running time. To address these problems, we propose HaCore for efficient coreset construction in VFL setting. HaCore first employs locality sensitive hashing (LSH) to map features to bit signatures locally on the clients, and then merges the local signatures for k-medoids clustering. Data samples that correspond to the medoids are added to the coreset. The core idea is that the distance of original data samples can be approximated by the Hamming distance between their LSH-based bit signatures. To accelerate k-medoids, we utilize an inverted index to search the nearest medoid and a bit-counting method to quickly compute the aggregate distance from many signatures to a medoid. We evaluate HaCore on 5 datasets and compare with state-of-the-art coreset construction methods for VFL. The results show that HaCore accelerates the best-performing baseline by over 45x and matches the accuracy of training with all samples.

PDF Details DOI

EAAI Journal 2025 Journal Article

Multi-scale fuzzy self-attention network for hyperspectral image classification with small-samples

Ziyi Li
Jindong Xu
Qianpeng Chong
Yu Yan

—With the widespread application of convolutional neural networks (CNN), significant breakthroughs have been achieved in hyperspectral image (HSI) classification. However, the lack of training samples remains one of the primary factors contributing to low classification performance. Moreover, HSIs may be affected by factors such as lighting conditions, environmental variations, and photographing distances during the collecting process, inevitably introducing noise. This noise significantly increases the uncertainty of the classification process, particularly in small sample scenarios. To alleviate these issues, a multi-scale fuzzy self-attention network (MFSAN) is proposed. Firstly, a multi-scale fuzzy embedding module (MFEM) is designed to effectively model fuzzy dependencies between features through three parallel paths, mitigating noise-induced uncertainty across multiple scales. Secondly, inspired by the principles of Transformers, a weighted dual-distance combined self-attention module (WD2CAM) is proposed to enhance global context representation by utilizing a novel spectral similarity measure. Finally, a new multiple feature extraction module is developed to fully exploit the rich information of HSIs under limited training samples. This module extracts spectral, spatial, and spectral-spatial features using multiple three-dimensional convolutions with different receptive fields. Experimental results on three datasets demonstrate that MFSAN achieves superior classification accuracy compared to state-of-the-art methods, with performance improvements in overall accuracy (OA) ranging from 1. 43 % to 9. 84 % under 1 % training samples.

Details DOI

EAAI Journal 2024 Journal Article

Fuzzy graph convolutional network for hyperspectral image classification

Jindong Xu
Kang Li
Ziyi Li
Qianpeng Chong
Haihua Xing
Qianguo Xing
Mengying Ni

—Graph convolutional network (GCN) has attracted much attention in the field of hyperspectral image classification for its excellent feature representation and convolution on arbitrarily structured non-Euclidean data. However, most state-of-the-art methods build a graph utilize the distance measure, which makes it challenging to fully characterize the complex relationship of hyperspectral remote sensing data. Moreover, the hyperspectral image usually has uncertainty introduced by the problems of the spectral variability and noise interference. This article uses fuzzy theory to optimize the GCN and thus solve the uncertainty problem in hyperspectral images, and presents a novel fuzzy graph convolutional network (F-GCN) for hyperspectral image classification. By calculating the fuzzy similarity of samples, a robust graph is first built rather than using the traditional Euclidean distance method, which allows a better representation of the complex relationship between hyperspectral remote sensing data. Furthermore, the proposed network introduces fuzzy layers into the model to cope with the ambiguity of the hyperspectral image. Finally, the classification results for three real-world hyperspectral data sets to show its feasibility and effectiveness in hyperspectral image classification.

Details DOI

EAAI Journal 2024 Journal Article

Pos-DANet: A dual-branch awareness network for small object segmentation within high-resolution remote sensing images

Qianpeng Chong
Mengying Ni
Jianjun Huang
Zongbao Liang
Jie Wang
Ziyi Li
Jindong Xu

The more detailed and accurate earth observation has been made driven by the progress of satellites and sensors optical photography technology, which poses both an opportunity and a challenge to small object segmentation task. However, the inherent difficulty and inadequate consideration still make small object segmentation task inevitably encounter a performance gain bottleneck. We analyze the longstanding but underestimated challenges in this task and give a peer-to-peer solution to response them. Specifically, we design a dual-branch awareness structure dedicated to small object segmentation, named Pos-DANet, which is composed with a small object activation branch and a fuzzy refinement branch. The small object activation branch is used to aware the small objects and avoid the negative influence of redundant background. The fuzzy refinement branch utilizes the fuzzy modeling to improve the segmentation accuracy of small objects. These two branches work collaboratively to make the whole structure to focus more on small objects and achieve satisfying segmentation results. Finally, we propose a hierarchical unbiased loss to eliminate the bias against small objects in the regression process. Extensive experiments demonstrated that Pos-DANet exhibits a higher qualitative and quantitative performance than the advanced methods within small objects, which achieves the best results in mIoU (71. 12 %, 83. 33 %) and sIoU (63. 23 %, 68. 89 %) on two datasets.

Details DOI