Zixian Su

Zixian Su

Auto-generated profile, based on publicly available information

Zixian Su

University of Liverpool, Liverpool, U.K.

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2019 in Chinese Physics B
Verified
Journal Article
Closed access
PDF file
ZSZixian Su
Zixian Su
YKYanzhuo Kang
Yanzhuo Kang
BZBofeng Zhang
Bofeng Zhang
ZZZhiqiang Zhang
Zhiqiang Zhang
HJHua Jiang
Hua Jiang
Previous studies presented the phase diagram induced by the disorder existing separately either in the higher-order topological states or in the topological trivial states, respectively. However, the influence of disorder on the system with the coexistence of the higher-order topological states and other traditional topological states has not been investigated. In this paper, we investigate the disorder induced phase transition in the magnetic higher-order topological insulator. By using the convolutional neural network and non-commutative geometry methods, two independent phase diagrams are calculated. With the comparison between these two diagrams, a topological transition from the normal insulator to the Chern insulator is confirmed. Furthermore, the network based on eigenstate wavefunction studies also presents a transition between the higher-order topological insulator and the Chern insulator.

3 May 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
ZSZixian Su
Zixian Su
KYKai Yao
Kai Yao
XYXi Yang
Xi Yang
QWQiu-Feng Wang
Qiu-Feng Wang
YYYuyao Yan
Yuyao Yan
Kaizhu HuangKaizhu Huang
Kaizhu Huang
Unsupervised cross-modality medical image adaptation aims to alleviate the severe domain gap between different imaging modalities without using the target domain label. A key in this campaign relies upon aligning the distributions of source and target domain. One common attempt is to enforce the global alignment between two domains, which, however, ignores the fatal local-imbalance domain gap problem, i.e., some local features with larger domain gap are harder to transfer. Recently, some methods conduct alignment focusing on local regions to improve the efficiency of model learning. While this operation may cause a deficiency of critical information from contexts. To tackle this limitation, we propose a novel strategy to alleviate the domain gap imbalance considering the characteristics of medical images, namely Global-Local Union Alignment . Specifically, a feature-disentanglement style-transfer module first synthesizes the target-like source images to reduce the global domain gap. Then, a local feature mask is integrated to reduce the ‘inter-gap’ for local features by prioritizing those discriminative features with larger domain gap. This combination of global and local alignment can precisely localize the crucial regions in segmentation target while preserving the overall semantic consistency. We conduct a series of experiments with two cross-modality adaptation tasks, i,e. cardiac substructure and abdominal multi-organ segmentation. Experimental results indicate that our method achieves state-of-the-art performance in both tasks.

21 October 2023
Verified
Conference Paper
Open access
KYKai Yao
Kai Yao
ZSZixian Su
Zixian Su
XYXi Yang
Xi Yang
Jie SunJie Sun
Jie Sun
Kaizhu HuangKaizhu Huang
Kaizhu Huang
In domain adaptive segmentation, domain shift may cause erroneous high-confidence predictions on the target domain, resulting in poor self-training. To alleviate the potential error, most previous works mainly consider aleatoric uncertainty arising from the inherit data noise. This may however lead to overconfidence in incorrect predictions and thus limit the performance. In this paper, we take advantage of Deterministic Uncertainty Methods (DUM) to explore the epistemic uncertainty, which reflects accurately the domain gap depending on the model choice and parameter fitting trained on source domain. The epistemic uncertainty on target domain is evaluated on-the-fly to facilitate online reweighting and correction in the self-training process. Meanwhile, to tackle the class-wise quantity and learning difficulty imbalance problem, we introduce a novel data resampling strategy to promote simultaneous convergence across different categories. This strategy prevents the class-level over-fitting in source domain and further boosts the adaptation performance by better quantifying the uncertainty in target domain. We illustrate the superiority of our method compared with the state-of-the-art methods.

17 March 2026 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JGJingwei Guo
Jingwei Guo
Kaizhu HuangKaizhu Huang
Kaizhu Huang
XYXinping Yi
Xinping Yi
ZSZixian Su
Zixian Su
RZRui Zhang
Rui Zhang
Whilst spectral graph neural networks (GNNs) are theoretically well-founded in the spectral domain, their practical reliance on polynomial approximation implies a profound linkage to the spatial domain. As previous studies rarely examine spectral GNNs from the spatial perspective, their spatial-domain interpretability remains elusive, e.g., what information is essentially encoded by spectral GNNs in the spatial domain? In this article, to answer this question, we investigate the theoretical connection between spectral filtering and spatial aggregation, unveiling an intrinsic interaction that spectral filtering implicitly leads the original graph to an adapted new graph, explicitly computed for spatial aggregation. Both theoretical and empirical investigations reveal that the adapted new graph not only exhibits nonlocality but also accommodates signed edge weights to reflect label consistency among nodes. These findings highlight the interpretable role of spectral GNNs in the spatial domain and inspire us to rethink graph spectral filters beyond the fixed-order polynomials, which limit the effective propagation range and hinder their ability to capture long-range dependencies. Built upon the theoretical findings, we revisit the state-of-the-art spectral GNNs and propose a novel spatially adaptive filtering (SAF) framework, which leverages the adapted new graph by spectral filtering for an auxiliary nonlocal aggregation. Notably, our SAF comprehensively models both node similarity and dissimilarity from a global perspective, therefore alleviating persistent deficiencies of GNNs related to long-range dependencies and graph heterophily. Extensive experiments over 13 node classification benchmarks demonstrate the superiority of our proposed framework to the state-of-the-art methods.