Author name cluster

Shichao Kan

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

2 author rows

AIIM Journal 2026 Journal Article

Leveraging artificial intelligence in advance care planning: A scoping review

Minghui Tan
Siyuan Tang
Zhao Ni
Shichao Kan
Paul Macharia
Haojie Zhang
Hao Yi
Guo Li

Background Advance care planning (ACP) is a process that enables individuals to discuss future health care decisions before they become seriously ill or unable to communicate. Artificial intelligence (AI) has demonstrated promising outcomes in facilitating healthcare, offering the potential to facilitate ACP. However, the current status of using AI to facilitate ACP is unclear. This study aimed to investigate how AI has been leveraged to facilitate ACP, with a particular focus on the intended purposes, AI algorithms used, data sources, and the performance of AI in achieving the intended purposes. Methods The methodology employed in this study adhered to the Scoping Review Methodological Framework. PubMed, EMBASE, Web of Science, CINAHL, Cochrane Library, and IEEE Xplore databases were searched from their inception to July 2025. Descriptive analyses and narrative synthesis were used to summarize findings from the included studies. Results A total of 42 eligible studies were analyzed. The studies were primarily used to detect ACP conversations and documents, identify patients needing ACP, promote ACP education, and explore linguistic features in ACP conversations. Rule-based natural language processing emerged as the most commonly used AI algorithm, with textual data being the primary modality employed. The included studies exhibited significant variation in performance evaluation. Finding The current use of AI in ACP remains limited in scope, primarily focusing on extracting ACP documentation from electronic health records and identifying patients who may benefit from ACP. The use of advanced technologies such as generative AI is limited, and performance evaluation primarily relies on discrimination metrics.

Details DOI

JBHI Journal 2025 Journal Article

CellCircLoc: Deep Neural Network for Predicting and Explaining Cell Line-Specific CircRNA Subcellular Localization

Min Zeng
Jingwei Lu
Yiming Li
Chengqian Lu
Shichao Kan
Fei Guo
Min Li

The subcellular localization of circular RNAs (circRNAs) is crucial for understanding their functional relevance and regulatory mechanisms. CircRNA subcellular localization exhibits variations across different cell lines, demonstrating the diversity and complexity of circRNA regulation within distinct cellular contexts. However, existing computational methods for predicting circRNA subcellular localization often ignore the importance of cell line specificity and instead train a general model on aggregated data from all cell lines. Considering the diversity and context-dependent behavior of circRNAs across different cell lines, it is imperative to develop cell line-specific models to accurately predict circRNA subcellular localization. In the study, we proposed CellCircLoc, a sequence-based deep learning model for circRNA subcellular localization prediction, which is trained for different cell lines. CellCircLoc utilizes a combination of convolutional neural networks, Transformer blocks, and bidirectional long short-term memory to capture both sequence local features and long-range dependencies within the sequences. In the Transformer blocks, CellCircLoc uses an attentive convolution mechanism to capture the importance of individual nucleotides. Extensive experiments demonstrate the effectiveness of CellCircLoc in accurately predicting circRNA subcellular localization across different cell lines, outperforming other computational models that do not consider cell line specificity. Moreover, the interpretability of CellCircLoc facilitates the discovery of important motifs associated with circRNA subcellular localization.

Details DOI

AAAI Conference 2025 Conference Paper

How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?

Wenjun Ding
Ying An
Lixing Chen
Shichao Kan
Fan Wu
Zhe Qu

Federated Adversarial Learning (FAL) is a robust framework for resisting adversarial attacks on federated learning. Although some FAL studies have developed efficient algorithms, they primarily focus on convergence performance and overlook generalization. Generalization is crucial for evaluating algorithm performance on unseen data. However, generalization analysis is more challenging due to non-smooth adversarial loss functions. A common approach to addressing this issue is to leverage smoothness approximation. In this paper, we develop algorithm stability measures to evaluate the generalization performance of two popular FAL algorithms: Vanilla FAL (VFAL) and Slack FAL (SFAL), using three different smooth approximation methods: 1) Surrogate Smoothness Approximation (SSA), (2) Randomized Smoothness Approximation (RSA), and (3) Over-Parameterized Smoothness Approximation (OPSA). Based on our in-depth analysis, we answer how to properly set the smoothness approximation method to mitigate generalization error in FAL. Moreover, we identify RSA as the most effective generalization error reduction method. In highly data-heterogeneous scenarios, we also recommend employing SFAL to mitigate the deterioration of generalization performance caused by heterogeneity. Based on our theoretical results, we provide insights to help develop more efficient FAL algorithms, such as designing new metrics and dynamic aggregation rules to mitigate heterogeneity.

PDF Details DOI

ICML Conference 2025 Conference Paper

Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation

Guoqing Zhang
Shichao Kan
Fanghui Zhang
Wanru Xu
Yue Zhang 0065
Yigang Cen

Scene Graph Generation (SGG) is a fundamental task in visual understanding, aimed at providing more precise local detail comprehension for downstream applications. Existing SGG methods often overlook the diversity of predicate representations and the consistency among similar predicates when dealing with long-tail distributions. As a result, the model’s decision layer fails to effectively capture details from the tail end, leading to biased predictions. To address this, we propose a Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization (NoDIS) method. On the one hand, expanding the predicate representation space enhances the model’s ability to learn both common and rare predicates, thus reducing prediction bias caused by data scarcity. We propose a conditional diffusion model to reconstructs features and increase the diversity of representations for same category predicates. On the other hand, independent predicate representations in the decision phase increase the learning complexity of the decision layer, making accurate predictions more challenging. To address this issue, we introduce a discretization mapper that learns consistent representations among similar predicates, reducing the learning difficulty and decision ambiguity in the decision layer. To validate the effectiveness of our method, we integrate NoDIS with various SGG baseline models and conduct experiments on multiple datasets. The results consistently demonstrate superior performance.

Details

IJCAI Conference 2023 Conference Paper

Singularformer: Learning to Decompose Self-Attention to Linearize the Complexity of Transformer

Yifan Wu
Shichao Kan
Min Zeng
Min Li

Transformers achieve excellent performance in a variety of domains since they can capture long-distance dependencies through the self-attention mechanism. However, self-attention is computationally costly due to its quadratic complexity and high memory consumption. In this paper, we propose a novel Transformer variant (Singularformer) that uses neural networks to learn the singular value decomposition process of the attention matrix to design a linear-complexity and memory-efficient global self-attention mechanism. Specifically, we decompose the attention matrix into the product of three matrix factors based on singular value decomposition and design neural networks to learn these matrix factors, then the associative law of matrix multiplication is used to linearize the calculation of self-attention. The above procedure allows us to compute self-attention as two-dimensional reduction processes in the first and second token dimensional spaces, followed by a multi-head self-attention computational process on the first dimensional reduced token features. Experimental results on 8 real-world datasets demonstrate that Singularformer performs favorably against the other Transformer variants with lower time and space complexity. Our source code is publicly available at https: //github. com/CSUBioGroup/Singularformer.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Coded Residual Transform for Generalizable Deep Metric Learning

Shichao Kan
Yixiong Liang
Min Li
Yigang Cen
Jianxin Wang
Zhihai He

A fundamental challenge in deep metric learning is the generalization capability of the feature embedding network model since the embedding network learned on training classes need to be evaluated on new test classes. To address this challenge, in this paper, we introduce a new method called coded residual transform (CRT) for deep metric learning to significantly improve its generalization capability. Specifically, we learn a set of diversified prototype features, project the feature map onto each prototype, and then encode its features using their projection residuals weighted by their correlation coefficients with each prototype. The proposed CRT method has the following two unique characteristics. First, it represents and encodes the feature map from a set of complimentary perspectives based on projections onto diversified prototypes. Second, unlike existing transformer-based feature representation approaches which encode the original values of features based on global correlation analysis, the proposed coded residual transform encodes the relative differences between the original features and their projected prototypes. Embedding space density and spectral decay analysis show that this multi perspective projection onto diversified prototypes and coded residual representation are able to achieve significantly improved generalization capability in metric learning. Finally, to further enhance the generalization performance, we propose to enforce the consistency on their feature similarity matrices between coded residual transforms with different sizes of projection prototypes and embedding dimensions. Our extensive experimental results and ablation studies demonstrate that the proposed CRT method outperform the state-of-the-art deep metric learning methods by large margins and improving upon the current best method by up to 4. 28% on the CUB dataset.

PDF Details