Author name cluster

Nan Chen

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.

9 papers

2 author rows

EAAI Journal 2026 Journal Article

A transferable framework for cross-city forecasting via invariant structural knowledge learning

Qianqian Zhou
Nan Chen

Cross-city forecasting is a key enabler for sustainable development in Intelligent Transportation Systems, supporting real-time forecasting services in cities with incomplete sensing infrastructures. Existing studies mainly focused on enhancing model generalization across cities with heterogeneous sensor distributions. However, we observe that these sensor layouts, despite their geographical discrepancies across cities, exhibit structure-related invariant mappings, which are inherently conducive to transfer learning. We thereby capture such invariant mappings by improving feature initialization and model design: 1) from a feature perspective, we mitigate inter-city structural discrepancies by initializing features with relative structural information derived from an improved graph structure; 2) from a training perspective, we update these features via inter-city correlations and enhance transferability by contrasting cross-city node heterogeneity. Specifically, we propose a Transferable Structural Knowledge Network (TSKNET) for cross-city traffic forecasting. TSKNET inserts virtual nodes into a pre-defined graph via exponential decay and initializes features using relative shortest paths to real-world nodes. We update features into invariant embeddings via inter-city node correlations and iteratively contrast embeddings across cities, quantifying cross-city heterogeneity through node-adapted weights. Finally, the weighted embeddings are encoded into transferable knowledge via a feature discriminator. We deploy TSKNET on four real-world traffic datasets (PEMS04, PEMS07, PEMS08, and Los-loop). Extensive experiments show that TSKNET surpasses competitive baselines by 6. 02 %–6. 79 % and boosts the interpretability of structural invariance learning.

Details DOI

EAAI Journal 2026 Journal Article

Contrast-enhanced heterogeneous multi-view graph for session-based recommendation via subsequence units

Fan Yang
Li Ji
Shuo Zhang
Dunlu Peng
Yiming Xu
Nan Chen

Session-based recommendation aims to capture user’s short-term dynamic preferences based on the dependencies between items within a session, and then predicts the next item that the user is most likely to interact with. Currently, session sequences are typically modeled as single-view structures, which focus on learning the interaction between individual items. However, these methods lack rich contextual information and are difficult to understand the user’s intent from a higher dimensional perspective. To better leverage the associations between contexts, this work proposes a Contrast-enhanced Heterogeneous Multi-view Graph via Subsequence Units (CHMGSU) for session-based recommendation. The sequences are modeled as both single-view and heterogeneous multi-view structures, where the single-view graph is constructed at the level of individual items to learn information transfer between items, while the heterogeneous multi-view graph is built using multiple consecutive items to better grasp the user’s high-dimensional intent. A hybrid readout function extracts the intent of subsequences, and captures relationships with contextual relevance. Next, single-view graph attention networks and heterogeneous multi-view graph neural networks are employed to generate item-level and subsequence-level embeddings. By fusing these two types of information, a session-level embedding with information from different perspectives is formed. The prediction results are optimized using the sample-adaptive loss function and the contrastive control gate. In addition, CHMGSU introduces Tmall, Gowalla, Diginetica and Nowplaying datasets to verify the effectiveness of the model on different types of datasets, and experimental results demonstrate that CHMGSU achieves consistent improvements over state-of-the-art baselines, thereby highlighting the incremental yet meaningful advancements achieved.

Details DOI

AAAI Conference 2025 Conference Paper

CustomContrast: A Multilevel Contrastive Perspective for Subject-Driven Text-to-Image Customization

Nan Chen
Mengqi Huang
Zhuowei Chen
Yang Zheng
Lei Zhang
Zhendong Mao

Subject-driven text-to-image (T2I) customization has drawn significant interest in academia and industry. This task enables pre-trained models to generate novel images based on unique subjects. Existing studies adopt a self-reconstructive perspective, focusing on capturing all details of a single image, which will misconstrue the specific image's irrelevant attributes (e.g., view, pose, and background) as the subject intrinsic attributes. This misconstruction leads to both overfitting or underfitting of irrelevant and intrinsic attributes of the subject, i.e., these attributes are over-represented or under-represented simultaneously, causing a trade-off between similarity and controllability. In this study, we argue an ideal subject representation can be achieved by a cross-differential perspective, i.e., decoupling subject intrinsic attributes from irrelevant attributes via contrastive learning, which allows the model to focus more on intrinsic attributes through intra-consistency (features of the same subject are spatially closer) and inter-distinctiveness (features of different subjects have distinguished differences). Specifically, we propose CustomContrast, a novel framework, which includes a Multilevel Contrastive Learning (MCL) paradigm and a Multimodal Feature Injection (MFI) Encoder. The MCL paradigm is used to extract intrinsic features of subjects from high-level semantics to low-level appearance through crossmodal semantic contrastive learning and multiscale appearance contrastive learning. To facilitate contrastive learning, we introduce the MFI encoder to capture cross-modal representations. Extensive experiments show the effectiveness of CustomContrast in subject similarity and text controllability.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Pro3D-Editor: A Progressive-Views Perspective for Consistent and Precise 3D Editing

Yang Zheng
Mengqi Huang
Nan Chen
Zhendong Mao

Text-guided 3D editing aims to precisely edit semantically relevant local 3D regions, which has significant potential for various practical applications ranging from 3D games to film production. Existing methods typically follow a view-indiscriminate paradigm: editing 2D views indiscriminately and projecting them back into 3D space. However, they overlook the different cross-view interdependencies, resulting in inconsistent multi-view editing. In this study, we argue that ideal consistent 3D editing can be achieved through a progressive-views paradigm, which propagates editing semantics from the editing-salient view to other editing-sparse views. Specifically, we propose Pro3D-Editor, a novel framework, which mainly includes Primary-view Sampler, Key-view Render, and Full-view Refiner. Primary-view Sampler dynamically samples and edits the most editing-salient view as the primary view. Key-view Render accurately propagates editing semantics from the primary view to other key views through its Mixture-of-View-Experts Low-Rank Adaption (MoVE-LoRA). Full-view Refiner edits and refines the 3D object based on the edited multi-views. Extensive experiments demonstrate that our method outperforms existing methods in editing accuracy and spatial consistency.

PDF Details

ICLR Conference 2024 Conference Paper

Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision

Nan Chen
Zemin Liu
Bryan Hooi
Bingsheng He
Rizal Fathony
Jun Hu 0016
Jia Chen 0011

Graph Anomaly Detection (GAD) has surfaced as a significant field of research, predominantly due to its substantial influence in production environments. Although existing approaches for node anomaly detection have shown effectiveness, they have yet to fully address two major challenges: operating in settings with limited supervision and managing class imbalance effectively. In response to these challenges, we propose a novel model, ConsisGAD, which is tailored for GAD in scenarios characterized by limited supervision and is anchored in the principles of consistency training. Under limited supervision, ConsisGAD effectively leverages the abundance of unlabeled data for consistency training by incorporating a novel learnable data augmentation mechanism, thereby introducing controlled noise into the dataset. Moreover, ConsisGAD takes advantage of the variance in homophily distribution between normal and anomalous nodes to craft a simplified GNN backbone, enhancing its capability to distinguish effectively between these two classes. Comprehensive experiments on several benchmark datasets validate the superior performance of ConsisGAD in comparison to state-of-the-art baselines. Our code is available at https://github.com/Xtra-Computing/ConsisGAD.

Details

YNICL Journal 2022 Journal Article

Fornix alterations induce the disruption of default mode network in patients with adamantinomatous craniopharyngiomas

Jie Kang
Lei Cao
Taoyang Yuan
Lu Jin
Yanjiao He
Xing Liu
Cuiping Zhang
Nan Chen

Adamantinomatous craniopharyngioma (ACPs) are rare embryonic tumors and often involve the hypothalamus. The underlying neural substrate of the hypothalamic involvement (HI)-related cognitive decline in patients with ACP is still unclear. We aimed to combine the multi-modal neuroimaging and histological characteristics of the ACP to explore the potential neural substrate of the HI-related cognitive decline. 45 patients with primary ACPs (invasive, 23; noninvasive, 22) and 52 healthy control subjects (HCs) were admitted to the cross-sectional study. No significant difference in cognitive domains was observed between HCs and patients with noninvasive ACPs (NACP). Patients with invasive ACPs (IACP) showed significantly lower working memory performance (WM, p = 0.002) than patients with NACP. The WM decline was correlated with the disruption of the medial temporal lobe (MTL) subsystem in the default mode network (DMN) (r = 0.45, p = 0.004). The increased radial diffusivity of the fornix, indicating demyelinating process, was correlated with the disruption of the MTL subsystem (r = -0.48, p = 0.002). Our study demonstrated that the fornix alterations link DMN disruption to HI-related cognitive decline in patients with ACPs. ACPs that invade the hypothalamus can provide a natural disease model to investigate the potential neural substrate of HI-related cognitive decline.

Details DOI

JBHI Journal 2020 Journal Article

MediMLP: Using Grad-CAM to Extract Crucial Variables for Lung Cancer Postoperative Complication Prediction

Tao He
Jixiang Guo
Nan Chen
Xiuyuan Xu
Zihuai Wang
Kaiyu Fu
Lunxu Liu
Zhang Yi

Lung cancer postoperative complication prediction (PCP) is significant for decreasing the perioperative mortality rate after lung cancer surgery. In this paper we concentrate on two PCP tasks: (1) the binary classification for predicting whether a patient will have postoperative complications; and (2) the three-class multi-label classification for predicting which postoperative complication a patient will experience. Furthermore, an important clinical requirement of PCP is the extraction of crucial variables from electronic medical records. We propose a novel multi-layer perceptron (MLP) model called medical MLP (MediMLP) together with the gradient-weighted class activation mapping (Grad-CAM) algorithm for lung cancer PCP. The proposed MediMLP, which involves one locally connected layer and fully connected layers with a shortcut connection, simultaneously extracts crucial variables and performs PCP tasks. The experimental results indicated that MediMLP outperformed normal MLP on two PCP tasks and had comparable performance with existing feature selection methods. Using MediMLP and further experimental analysis, we found that the variable of “time of indwelling drainage tube” was very relevant to lung cancer postoperative complications.

Details DOI

YNICL Journal 2019 Journal Article

Reorganization of the somatosensory pathway after subacute incomplete cervical cord injury

Qian Chen
Weimin Zheng
Xin Chen
Xuejing Li
Ling Wang
Wen Qin
Kuncheng Li
Nan Chen

OBJECTIVE: The main purpose of the present study was to investigate the possible somatosensory-related brain functional reorganization after traumatic spinal cord injury (SCI). METHODS: Thirteen patients with subacute incomplete cervical cord injury (ICCI) and thirteen age- and sex-matched healthy controls (HCs) were recruited. Eleven patients and all the HCs underwent both sensory task-related brain functional scanning and whole brain structural scanning on a 3.0 Tesla MRI system, and two patients underwent only structural scanning; the process of structural scanning was completed on thirteen patients, while functional scanning was only applied to eleven patients. We performed sensory task-related functional MRI (fMRI) to investigate the functional changes in the brain. In addition, voxel-based morphometry (VBM) was applied to explore whether any sensory-related brain structural changes occur in the whole brain after SCI. RESULTS: Compared with HCs, ICCI patients exhibited decreased activation in the left postcentral gyrus (postCG), the brainstem (midbrain and right pons) and the right cerebellar lobules IV-VI. Moreover, a significant positive association was found between the activation in the left PostCG and the activation in both the brainstem and the right cerebellar lobules IV-VI. Additionally, the decrease in gray matter volume (GMV) was detected in the left superior parietal lobule (SPL). The decrease of white matter volume (WMV) was observed in the right temporal lobe, the right occipital lobe, and the right calcarine gyrus. No structural change in the primary sensory cortex (S1), the secondary somatosensory cortex (S2) or the thalamus was detected. CONCLUSION: These functional and structural findings may demonstrate the existence of an alternative pathway in the impairment of somatosensory function after SCI, which consists of the ipsilateral cerebellum, the brainstem and the contralateral postCG. It provides a new theoretical basis for the mechanism of sensory-related brain alteration in SCI patients and the rehabilitation therapy based on this pathway in the future.

Details DOI

YNICL Journal 2018 Journal Article

Gray-matter-specific MR imaging improves the detection of epileptogenic zones in focal cortical dysplasia: A new sequence called fluid and white matter suppression (FLAWS)

Xin Chen
Tianyi Qian
Tobias Kober
Guojun Zhang
Zhiwei Ren
Tao Yu
Yueshan Piao
Nan Chen

Objectives: To evaluate the diagnostic value and characteristic features of FCD epileptogenic zones using a novel sequence called fluid and white matter suppression (FLAWS). Materials and methods: Thirty-nine patients with pathologically confirmed FCD and good surgery outcomes (class I or II, according to the Engel Epilepsy Surgery Outcome Scale) were retrospectively included in the study. All the patients underwent a preoperative whole-brain MRI examination that included conventional sequences (T2WI, T1WI, two-dimensional (2D) axial, coronal fluid-attenuated inversion recovery [FLAIR]) and FLAWS. An additional 3D-FLAIR MRI sequence was performed in 17 patients. To evaluate the sensitivity and specificity of FLAWS and investigate the cause of false-positives, 36 healthy volunteers were recruited as normal controls. Two radiologists evaluated all the image data. The detection rates of the FCD epileptogenic zone on different sequences were compared based on five criteria: abnormal cortical morphology (thickening, thinning, or abnormally deep sulcus); abnormal cortical signal intensity; blurred gray-white matter junction; abnormal signal intensity of the subcortical white matter, and the transmantle sign. The sensitivity and specificity of FLAWS for detecting the FCD lesions were calculated with the reviewers blinded to all the clinical information, i.e. to the patient identity and the location of the resected regions. To explore how many features were sufficient for the diagnosis of the epileptogenic zones, the frequency of each criterion in the resected regions and their combinations were assessed on FLAWS, according to the results of the assessment when the reviewers were aware of the location of the resected regions. Based on the findings of the 17 patients with an additional 3D-FLAIR scan when the reviewers were aware of the location of the resected regions, quantitative analysis of the regions of interest was used to compare the tissue contrast among 2D-axial FLAIR, 3D-FLAIR, and the FLAWS sequence. Visualization score analysis was used to evaluate the visualization of the five features on conventional, 3D-FLAIR, and FLAWS images. Finally, to explore the reason for false-positive results, a further evaluation of the whole brain FLAWS images was conducted for all the subjects. Results: The sensitivity and specificity for detecting the FCD lesions on the FLAWS sequence were 71.9% and 71.1%, respectively. When the reviewers were blinded to the location of the resected regions, the detection rate of the FLAWS sequence was significantly higher than that of the conventional sequences (P = 0.00). In the 17 patients who underwent an additional 3D FLAIR scan, no statistically significant difference was found between the FLAWS and the 3D-FLAIR (P = 0.25). All the patients had at least two imaging features, one of which was "the blurred junction of the gray-white matter." The transmantle sign, which is widely believed to be a specific feature of FCD type II, could also be observed in type I on the FLAWS sequence. The relative tissue contrast of FLAWS was higher than that of the 2D-FLAIR with respect to lesion/white matter (WM), deep gray matter (GM)/WM, and cortex/WM (P = 0.00 for all three measures) and higher than that of the 3D-FLAIR with respect to the lesion/WM (P = 0.01). The visualization score analysis showed that the visualization of FLAWS was more enhanced than that of the conventional and 3D-FLAIR images with respect to the blurred junction (P = 0.00 for both comparisons) and the abnormal signal intensity of the subcortical white matter (P = 0.01 for both comparisons). The thin-threadlike signal and individual FCD features outside the epileptogenic regions were considered the primary cause of the false-positive results of FLAWS. Conclusions: FLAWS can help in the detection of FCD epileptogenic zones. It is recommended that epileptogenic zone on FLAWS be diagnosed based on a combination of two features, one of which should be the "blurred junction of the gray-white matter" in types I and II. In type III, the combination of "the blurred junction of the gray-white matter" with "abnormal signal intensity of subcortical white matter" is recommended.

Details DOI