Author name cluster

Jian 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.

12 papers

2 author rows

TIST Journal 2026 Journal Article

FedPRS: A Privacy-preserving Representation Synthesis Framework for Federated Contribution Evaluation

Yuwei Fan
Yuan Yao
Wei Xi
Quan Zhao
Zelei Liu
Lixin Fan
Qiang Yang
Jian Jin

Federated Learning (FL) enables the collaborative training of a global model while protecting participants’ privacy. Evaluating each participant’s contribution is essential to providing a high-quality model, ensuring fairness, and mitigating potential biases. Most existing contribution evaluation approaches for FL assume that the server has a public validation dataset. However, it is almost impossible to obtain a validation dataset due to privacy concerns. In this article, we propose a Federated Privacy-preserving Representation Synthesis (FedPRS) framework to synthesize a validation dataset for contribution evaluation. The proposed FedPRS framework first transforms each participant’s private validation dataset into its representation. Then, a random-region desensitization strategy is developed to further desensitize the dataset without compromising its utility. The desensitized representation dataset of each participant is collected by the server to evaluate federated contribution, which considers both equity and privacy protection. Moreover, we instantiate and integrate three specific contribution evaluation approaches in this framework. We perform experiments on various FL settings, including independently identically distributed (IID) and non-IID data distributions. Experimental results demonstrate that the contribution evaluation results obtained using the validation dataset synthesized by the FedPRS framework are closely aligned with those obtained using a real, private validation dataset.

Details DOI

AAAI Conference 2026 Conference Paper

Hashed Watermark as a Filter: A Unified Defense Against Forging and Overwriting Attacks in Neural Network Watermarking

Yuan Yao
Jin Song
Jian Jin

As valuable digital assets, deep neural networks necessitate robust ownership protection, positioning neural network watermarking (NNW) as a promising solution. Among various NNW approaches, weight-based methods are favored for their simplicity and practicality; however, they remain generally vulnerable to forging and overwriting attacks. To address those challenges, we propose *NeuralMark*, a robust method built around a *hashed watermark filter*. Specifically, we utilize a hash function to generate an irreversible binary watermark from a secret key, which is then used as a filter to select the model parameters for embedding. This design cleverly intertwines the embedding parameters with the hashed watermark, providing a robust defense against both forging and overwriting attacks. Average pooling is also incorporated to resist fine-tuning and pruning attacks. Furthermore, it can be seamlessly integrated into various neural network architectures, ensuring broad applicability. We theoretically analyze its security boundary and highlight the necessity of using a hashed watermark as a filtering mechanism. Empirically, we demonstrate its effectiveness and robustness across 13 distinct Convolutional and Transformer architectures, covering five image classification tasks and one text generation task.

PDF Details DOI

AAAI Conference 2026 Conference Paper

The Last Byte: Learning Just Enough for Machine-Oriented Image Compression

Wuyuan Xie
Zhenming Li
Ye Liu
Jian Jin
Yun Song
Miaohui Wang

Just recognizable distortion (JRD) has been introduced for image compression for machines, aiming to quantify the maximum coding distortion that can be tolerated by a specific perception model, thereby defining the upper bound of machine vision redundancy (MVR). However, existing JRD-based redundancy estimation methods face three key challenges: limited dataset annotation accuracy, low prediction efficiency, and insufficient perception accuracy, all of which hinder their practical deployment. To address these limitations, we propose a new MVR-Net, a frame-wise efficient JRD prediction method that generates the optimal encoding quantization map in a single inference pass. Furthermore, we refine the annotation standard for JRD datasets based on experimental insights, enhancing the precision of recognizable redundancy measurement. Compared to stateof-the-art methods, MVR-Net achieves a superior balance between bitrate reduction and perception accuracy in JRD-guided compression, while offering up to a 40,000× speed improvement, demonstrating its practicality and efficiency for real-world applications.

PDF Details DOI

ICML Conference 2025 Conference Paper

Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization

Yang Shen 0006
Xiu-Shen Wei
Yifan Sun 0003
Yuxin Song
Tao Yuan
Jian Jin
He-Yang Xu
Yazhou Yao

Computer Vision (CV) has yet to fully achieve the zero-shot task generalization observed in Natural Language Processing (NLP), despite following many of the milestones established in NLP, such as large transformer models, extensive pre-training, and the auto-regression paradigm, among others. In this paper, we rethink the reality that CV adopts discrete and terminological task definitions (e. g. , "image segmentation"), and conjecture it is a key barrier that hampers zero-shot task generalization. Our hypothesis is that without truly understanding previously-seen tasks—due to these terminological definitions—deep models struggle to generalize to novel tasks. To verify this, we introduce Explanatory Instructions, which provide an intuitive way to define CV task objectives through detailed linguistic transformations from input images to outputs. We create a large-scale dataset comprising 12 million "image input $\to$ explanatory instruction $\to$ output" triplets, and train an auto-regressive-based vision-language model (AR-based VLM) that takes both images and explanatory instructions as input. By learning to follow these instructions, the AR-based VLM achieves instruction-level zero-shot capabilities for previously-seen tasks and demonstrates strong zero-shot generalization for unseen CV tasks. Code and dataset will be open-sourced.

Details

AAAI Conference 2025 Conference Paper

Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels

Xin-yang Zhao
Jian Jin
Yang-yang Li
Yazhou Yao

The Coarse-to-Fine Few-Shot (C2FS) task is designed to train models using only coarse labels, then leverages a limited number of subclass samples to achieve fine-grained recognition capabilities. This task presents two main challenges: coarse-grained supervised pre-training suppresses the extraction of critical fine-grained features for subcategory discrimination, and models suffer from overfitting due to biased distributions caused by limited fine-grained samples. In this paper, we propose the Twofold Debiasing (TFB) method, which addresses these challenges through detailed feature enhancement and distribution calibration. Specifically, we introduce a multi-layer feature fusion reconstruction module and an intermediate layer feature alignment module to combat the model's tendency to focus on simple predictive features directly related to coarse-grained supervision, while neglecting complex fine-grained level details. Furthermore, we mitigate the biased distributions learned by the fine-grained classifier using readily available coarse-grained sample embeddings enriched with fine-grained information. Extensive experiments conducted on five benchmark datasets demonstrate the efficacy of our approach, achieving state-of-the-art results that surpass competitive methods.

PDF Details DOI

ICML Conference 2024 Conference Paper

Rethinking Guidance Information to Utilize Unlabeled Samples: A Label Encoding Perspective

Yulong Zhang 0005
Yuan Yao 0016
Shuhao Chen
Pengrong Jin
Yu Zhang 0006
Jian Jin
Jiangang Lu

Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples. A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their learning. However, EntMin emphasizes prediction discriminability while neglecting prediction diversity. To alleviate this issue, in this paper, we rethink the guidance information to utilize unlabeled samples. By analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label encoding. Inspired by this finding, we propose a Label-Encoding Risk Minimization (LERM). It first estimates the label encodings through prediction means of unlabeled samples and then aligns them with their corresponding ground-truth label encodings. As a result, the LERM ensures both prediction discriminability and diversity, and it can be integrated into existing methods as a plugin. Theoretically, we analyze the relationships between LERM and ERM as well as EntMin. Empirically, we verify the superiority of the LERM under several label insufficient scenarios. The codes are available at https: //github. com/zhangyl660/LERM.

Details

AAAI Conference 2024 Conference Paper

Semantic Lens: Instance-Centric Semantic Alignment for Video Super-resolution

Qi Tang
Yao Zhao
Meiqin Liu
Jian Jin
Chao Yao

As a critical clue of video super-resolution (VSR), inter-frame alignment significantly impacts overall performance. However, accurate pixel-level alignment is a challenging task due to the intricate motion interweaving in the video. In response to this issue, we introduce a novel paradigm for VSR named Semantic Lens, predicated on semantic priors drawn from degraded videos. Specifically, video is modeled as instances, events, and scenes via a Semantic Extractor. Those semantics assist the Pixel Enhancer in understanding the recovered contents and generating more realistic visual results. The distilled global semantics embody the scene information of each frame, while the instance-specific semantics assemble the spatial-temporal contexts related to each instance. Furthermore, we devise a Semantics-Powered Attention Cross-Embedding (SPACE) block to bridge the pixel-level features with semantic knowledge, composed of a Global Perspective Shifter (GPS) and an Instance-Specific Semantic Embedding Encoder (ISEE). Concretely, the GPS module generates pairs of affine transformation parameters for pixel-level feature modulation conditioned on global semantics. After that the ISEE module harnesses the attention mechanism to align the adjacent frames in the instance-centric semantic space. In addition, we incorporate a simple yet effective pre-alignment module to alleviate the difficulty of model training. Extensive experiments demonstrate the superiority of our model over existing state-of-the-art VSR methods.

PDF Details DOI

IJCAI Conference 2022 Conference Paper

CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction

Jiaju Lin
Qin Chen
Jie Zhou
Jian Jin
Liang He

Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document. Most previous work focuses on learning the direct relations between arguments and the given trigger, while the implicit relations with long-range dependency are not well studied. Moreover, recent neural network based approaches rely on a large amount of labeled data for training, which is unavailable due to the high labelling cost. In this paper, we propose a Curriculum learning based Prompt tuning (CUP) approach, which resolves implicit EAE by four learning stages. The stages are defined according to the relations with the trigger node in a semantic graph, which well captures the long-range dependency between arguments and the trigger. In addition, we integrate a prompt-based encoder-decoder model to elicit related knowledge from pre-trained language models (PLMs) in each stage, where the prompt templates are adapted with the learning progress to enhance the reasoning for arguments. Experimental results on two well-known benchmark datasets show the great advantages of our proposed approach. In particular, we outperform the state-of-the-art models in both fully-supervised and low-data scenarios.

PDF Details DOI

EAAI Journal 2016 Journal Article

A biclustering-based method for market segmentation using customer pain points

Binda Wang
Yunwen Miao
Hongya Zhao
Jian Jin
Yizeng Chen

Market segmentation plays a crucial role in product design and development. However, conventional segmentation approaches based on one-way cluster analysis techniques have met two special challenges in practice. First, conventional approaches that derive a global result rather than a local one fail to cluster customers into such groups who have similar characteristics on a fraction of variables. Second, since there is no formal mechanism to select appropriate segmentation variables, different combination of variables will obtain different segmentation results, which makes the approaches not quite convincing. To overcome the two limitations, a novel biclustering-based market segmentation method by using customer pain points is proposed in this paper. Different from one-way algorithms clustering only rows or only columns, biclustering algorithms cluster both rows associated with customers and columns associated with customer pain points simultaneously to identify homogenous subgroups of customers with common characteristics towards a subset of segmentation variables. In addition, customer pain points are used to replace traditional segmentation variables in the presented method, which makes the results more reasonable. Subsequently, an illustrated example is studied to demonstrate the effectiveness of the presented method.

Details DOI

EAAI Journal 2016 Journal Article

Identifying comparative customer requirements from product online reviews for competitor analysis

Jian Jin
Ping Ji
Rui Gu

A large volume of product online reviews are generated from time to time, which contain rich information regarding customer requirements. These reviews help designers to make exhaustive analyses of competitors, which is one indispensable step in market-driven product design. How to extract critical opinionated sentences associated with some specific features from product online reviews has been investigated by some researchers. However, few of them examined how to employ these valuable resources for competitor analysis. Hence, in this research, a framework is illustrated to select pairs of opinionated representative yet comparative sentences with specific product features from reviews of competitive products. With the help of the techniques on sentiment analysis, opinionated sentences referring to a specific feature are first identified from product online reviews. Then, information representativeness, information comparativeness and information diversity are investigated for the selection of a small number of representative yet comparative opinionated sentences. Accordingly, an optimization problem is formulated, and three greedy algorithms are proposed to analyze this problem for suboptimal solutions. Finally, with a large amount of real data from Amazon. com, categories of extensive experiments are conducted and the final encouraging results are realized, which prove the effectiveness of the proposed approach.

Details DOI

EAAI Journal 2016 Journal Article

What makes consumers unsatisfied with your products: Review analysis at a fine-grained level

Jian Jin
Ping Ji
C.K. Kwong

Online product reviews contain valuable information regarding customer requirements (CRs). Intelligent analysis of a large volume of online CRs attracts interest from researchers in various fields. However, many research studies only concern sentiment polarity in the product feature level. With these results, designers still need to read a list of reviews to absorb comprehensive CRs. In this research, online reviews are analyzed at a fine-grained level. In particular, aspects of product features and detailed reasons of consumers are extracted from online reviews to inform designers regarding what leads to unsatisfied opinions. This research starts from the identification of product features and the sentiment analysis with the help of pros and cons reviews. Next, the approach of conditional random fields is employed to detect aspects of product features and detailed reasons from online reviews jointly. In addition, a co-clustering algorithm is devised to group similar aspects and reasons to provide a concise description about CRs. Finally, utilizing customer reviews of six mobiles in Amazon. com, a case study is presented to illustrate how the proposed approaches benefit product designers in the elicitation of CRs by the analysis of online opinion data.

Details DOI

EAAI Journal 2015 Journal Article

Translating online customer opinions into engineering characteristics in QFD: A probabilistic language analysis approach

Jian Jin
Ping Ji
Ying Liu
S.C. Johnson Lim

Online opinions provide informative customer requirements for product designers. However, the increasing volume of opinions make them hard to be digested entirely. It is expected to translate online opinions for designers automatically when they are launching a new product. In this research, an exploratory study is conducted, in which customer requirements in online reviews are manually translated into engineering characteristics (ECs) for Quality function deployment (QFD). From the exploratory study, a simple mapping from keywords to ECs is observed not able to be built. It is also found that it will be a time-consuming task to translate a large number of reviews. Accordingly, a probabilistic language analysis approach is proposed, which translates reviews into ECs automatically. In particular, the statistic concurrence information between keywords and nearby words is analyzed. Based on the unigram model and the bigram model, an integrated impact learning algorithm is advised to estimate the impacts of keywords and nearby words respectively. The estimated impacts are utilized to infer which ECs are implied in a given context. Using four brands of printer reviews from Amazon. com, comparative experiments are conducted. Finally, an illustrative example is shown to clarify how this approach can be applied by designers in QFD.

Details DOI