Author name cluster

Dian Jin

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

AAAI Conference 2026 Conference Paper

Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks

Dian Jin
Yancheng Yuan
Xiaoming Tao

Pretrained equivariant graph neural networks based on spherical harmonics offer efficient and accurate alternatives to computationally expensive ab-initio methods, yet adapting them to new tasks and chemical environments still requires fine-tuning. Conventional parameter-efficient fine-tuning (PEFT) techniques, such as Adapters and LoRA, typically break symmetry, making them incompatible with those equivariant architectures. ELoRA, recently proposed, is the first equivariant PEFT method. It achieves improved parameter efficiency and performance on many benchmarks. However, the relatively high degrees of freedom it retains within each tensor order can still perturb pretrained feature distributions and ultimately degrade performance. To address this, we present Magnitude-Modulated Equivariant Adapter (MMEA), a novel equivariant fine-tuning method which employs lightweight scalar gating to modulate feature magnitudes on a per-order and per-multiplicity basis. We demonstrate that MMEA preserves strict equivariance and, across multiple benchmarks, consistently improves energy and force predictions to state-of-the-art levels while training fewer parameters than competing approaches. These results suggest that, in many practical scenarios, modulating channel magnitudes is sufficient to adapt equivariant models to new chemical environments without breaking symmetry, pointing toward a new paradigm for equivariant PEFT design.

PDF Details DOI

JBHI Journal 2026 Journal Article

OPDoctorNet: Deep Learning Revolutionizes Opportunistic Screening of Osteoporosis Based on Clinical Data

Qiankun Jin
Qiyu Jia
Xiaoxia Zhou
Dian Jin
Xuewei Song
Zhiyuan Xie
Abudusalamu Alimujiang
Yancheng Li

Osteoporosis poses a significant global public health challenge, and timely detection and treatment are crucial for preventing fragility fractures in the elderly. However, opportunistic screening remains challenging. Despite rapid deep learning development, its potential in clinical data classification has yet to be fully realized, with traditional machine learning dominating. Therefore, deepening research on deep learning for clinical data recognition in osteoporosis screening holds practical significance. This study utilizes the latest artificial intelligence technology to develop the OPDoctorNet algorithm, combining Transformer and Mamba feature extraction advantages, innovatively proposing multiscale feature fusion and the FeatureBake Block to deeply extract global and local features. The algorithm improves osteoporosis recognition accuracy in clinical data and meets multi-task needs. Results show OPDoctorNet significantly outperforms traditional machine learning and other AI methods in accuracy, recall, and F1 scores, with strong robustness and generalization. Through the Innovation of the FeatureBake Block, this study provides a groundbreaking solution for Transformer and Mamba feature processing, enabling efficient, accurate opportunistic osteoporosis screening. Additionally, using SHAP Plot and feature importance mapping for visual analysis enhances interpretability, offering new ideas and methods for osteoporosis screening in clinical practice, aiding accurate, scientific clinical decision-making and promoting deep learning application in clinical data classification.

Details DOI

AAAI Conference 2025 Conference Paper

Just a Few Glances: Open-Set Visual Perception with Image Prompt Paradigm

Jinrong Zhang
Penghui Wang
Chunxiao Liu
Wei Liu
Dian Jin
Qiong Zhang
Erli Meng
Zhengnan Hu

To break through the limitations of pre-training models on fixed categories, Open-Set Object Detection (OSOD) and Open-Set Segmentation (OSS) have attracted a surge of interest from researchers. Inspired by large language models, mainstream OSOD and OSS methods generally utilize text as a prompt, achieving remarkable performance. Following SAM paradigm, some researchers use visual prompts, such as points, boxes, and masks that cover detection or segmentation targets. Despite these two prompt paradigms exhibit excellent performance, they also reveal inherent limitations. On the one hand, it is difficult to accurately describe characteristics of specialized category using textual description. On the other hand, existing visual prompt paradigms heavily rely on multi-round human interaction, which hinders them being applied to fully automated pipeline. To address the above issues, we propose a novel prompt paradigm in OSOD and OSS, that is, Image Prompt Paradigm. This brand new prompt paradigm enables to detect or segment specialized categories without multi-round human intervention. To achieve this goal, the proposed image prompt paradigm uses just a few image instances as prompts, and we propose a novel framework named MI Grounding for this new paradigm. In this framework, high-quality image prompts are automatically encoded, selected and fused, achieving the single-stage and non-interactive inference. We conduct extensive experiments on public datasets, showing that MI Grounding achieves competitive performance on OSOD and OSS benchmarks compared to text prompt paradigm methods and visual prompt paradigm methods. Moreover, MI Grounding can greatly outperform existing method on our constructed specialized ADR50K dataset.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

Haixin Wang
Xinlong Yang
Jianlong Chang
Dian Jin
Jinan Sun
Shikun Zhang
Xiao Luo
Qi Tian

Driven by the progress of large-scale pre-training, parameter-efficient transfer learning has gained immense popularity across different subfields of Artificial Intelligence. The core is to adapt the model to downstream tasks with only a small set of parameters. Recently, researchers have leveraged such proven techniques in multimodal tasks and achieve promising results. However, two critical issues remain unresolved: how to further reduce the complexity with lightweight design and how to boost alignment between modalities under extremely low parameters. In this paper, we propose A gracefUl pRompt framewOrk for cRoss-modal trAnsfer (AURORA) to overcome these challenges. Considering the redundancy in existing architectures, we first utilize the mode approximation to generate 0. 1M trainable parameters to implement the multimodal parameter-efficient tuning, which explores the low intrinsic dimension with only 0. 04% parameters of the pre-trained model. Then, for better modality alignment, we propose the Informative Context Enhancement and Gated Query Transformation module under extremely few parameters scenes. A thorough evaluation on six cross-modal benchmarks shows that it not only outperforms the state-of-the-art but even outperforms the full fine-tuning approach. Our code is available at: https: //github. com/WillDreamer/Aurora.

PDF Details

NeurIPS Conference 2021 Conference Paper

Unique sparse decomposition of low rank matrices

Dian Jin
Xin Bing
Yuqian Zhang

The problem of finding the unique low dimensional decomposition of a given matrix has been a fundamental and recurrent problem in many areas. In this paper, we study the problem of seeking a unique decomposition of a low-rank matrix $Y\in \mathbb{R}^{p\times n}$ that admits a sparse representation. Specifically, we consider $ Y = AX\in \mathbb{R}^{p\times n}$ where the matrix $A\in \mathbb{R}^{p\times r}$ has full column rank, with $r < \min\{n, p\}$, and the matrix $X\in \mathbb{R}^{r\times n}$ is element-wise sparse. We prove that this sparse decomposition of $Y$ can be uniquely identified by recovering ground-truth $A$ column by column, up to some intrinsic signed permutation. Our approach relies on solving a nonconvex optimization problem constrained over the unit sphere. Our geometric analysis for the nonconvex optimization landscape shows that any {\em strict} local solution is close to the ground truth solution, and can be recovered by a simple data-driven initialization followed with any second-order descent algorithm. At last, we corroborate these theoretical results with numerical experiments

PDF Details