Author name cluster

Xi Yu

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 2024 Journal Article

A dyeing clustering algorithm based on ant colony path-finding mechanism

Shijie Zeng
Yuefei Wang
Xi Yu
Haojie Song
Xiaoyan Guo
Zheheng Li

Clustering has a wide range of applications in various industries. In different research ideas, bionic algorithms have heuristic help for clustering research. However, most of the clustering algorithms based on bionics often have problems of insufficient information extraction, too many required parameters, and limited application scope. Therefore, these algorithms have lower accuracy than traditional clustering algorithms. To solve these problems, this paper proposes a new ant colony clustering algorithm, which is called Dyeing Clustering Algorithm based on Ant Colony Path-finding. This algorithm combines the idea of dyeing with pheromones for the first time and realizes clustering by using ants to crawl and dye each point, bringing new inspiration to the artificial intelligence research. This can better capture data features, improve fault tolerance and achieve a better clustering effect. In addition, the algorithm is constructed as a dynamic system to deeply mine data information with the strategy of swarm intelligence, including the ant colony generation model, path-finding model, path-finding termination model, and dyeing clustering model. Besides, to evaluate the algorithm, we selected 2 simulation data sets, 5 artificial data sets, 5 real-world data sets, 13 comparison algorithms, and 8 evaluation indexes. From the comprehensive multi-round experiments, seven of the eight evaluation indexes of the Dyeing Clustering Algorithm based on Ant Colony Path-finding algorithm are more advantageous than other comparison algorithms, which demonstrates its enormous potential in industrial applications.

Details DOI

ICLR Conference 2024 Conference Paper

Cauchy-Schwarz Divergence Information Bottleneck for Regression

Shujian Yu
Xi Yu
Sigurd Løkse
Robert Jenssen
José C. Príncipe

The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\mathbf{t}$ by striking a trade-off between a compression term $I(\mathbf{x};\mathbf{t})$ and a prediction term $I(y;\mathbf{t})$, where $I(\cdot;\cdot)$ refers to the mutual information (MI). MI is for the IB for the most part expressed in terms of the Kullback-Leibler (KL) divergence, which in the regression case corresponds to prediction based on mean squared error (MSE) loss with Gaussian assumption and compression approximated by variational inference. In this paper, we study the IB principle for the regression problem and develop a new way to parameterize the IB with deep neural networks by exploiting favorable properties of the Cauchy-Schwarz (CS) divergence. By doing so, we move away from MSE-based regression and ease estimation by avoiding variational approximations or distributional assumptions. We investigate the improved generalization ability of our proposed CS-IB and demonstrate strong adversarial robustness guarantees. We demonstrate its superior performance on six real-world regression tasks over other popular deep IB approaches. We additionally observe that the solutions discovered by CS-IB always achieve the best trade-off between prediction accuracy and compression ratio in the information plane. The code is available at \url{https://github.com/SJYuCNEL/Cauchy-Schwarz-Information-Bottleneck}.

Details

NeurIPS Conference 2024 Conference Paper

CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment

Xi Yu
Shinjae Yoo
Yuewei Lin

Domain generalization (DG) is a fundamental yet challenging topic in machine learning. Recently, the remarkable zero-shot capabilities of the large pre-trained vision-language model (e. g. , CLIP) have made it popular for various downstream tasks. However, the effectiveness of this capacity often degrades when there are shifts in data distribution during testing compared to the training data. In this paper, we propose a novel method, known as CLIPCEIL, a model that utilizes Channel rEfinement and Image-text aLignment to facilitate the CLIP to the inaccessible $\textit{out-of-distribution}$ test datasets that exhibit domain shifts. Specifically, we refine the feature channels in the visual domain to ensure they contain domain-invariant and class-relevant features by using a lightweight adapter. This is achieved by minimizing the inter-domain variance while maximizing the inter-class variance. In the meantime, we ensure the image-text alignment by aligning text embeddings of the class descriptions and their corresponding image embedding while further removing the domain-specific features. Moreover, our model integrates multi-scale CLIP features by utilizing a self-attention fusion module, technically implemented through one Transformer layer. Extensive experiments on five widely used benchmark datasets demonstrate that CLIPCEIL outperforms the existing state-of-the-art methods. The source code is available at \url{https: //github. com/yuxi120407/CLIPCEIL}.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model for Image Editing

Xi Yu
Xiang Gu
Haozhi Liu
Jian Sun

Score-based diffusion models (SBDMs) have achieved state-of-the-art results in image generation. In this paper, we propose a Non-isotropic Gaussian Diffusion Model (NGDM) for image editing, which requires editing the source image while preserving the image regions irrelevant to the editing task. We construct NGDM by adding independent Gaussian noises with different variances to different image pixels. Instead of specifically training the NGDM, we rectify the NGDM into an isotropic Gaussian diffusion model with different pixels having different total forward diffusion time. We propose to reverse the diffusion by designing a sampling method that starts at different time for different pixels for denoising to generate images using the pre-trained isotropic Gaussian diffusion model. Experimental results show that NGDM achieves state-of-the-art performance for image editing tasks, considering the trade-off between the fidelity to the source image and alignment with the desired editing target.

PDF Details

YNIMG Journal 2022 Journal Article

Brain intrinsic connection patterns underlying tool processing in human adults are present in neonates and not in macaques

Haojie Wen
Ting Xu
Xiaoying Wang
Xi Yu
Yanchao Bi

Tool understanding and use are supported by a dedicated left-lateralized, intrinsically connected network in the human adult brain. To examine this network's phylogenetic and ontogenetic origins, we compared resting-state functional connectivity (rsFC) among regions subserving tool processing in human adults to rsFC among homologous regions in human neonates and macaque monkeys (adolescent and mature). These homologous regions formed an intrinsic network in human neonates, but not in macaques. Network topological patterns were highly similar between human adults and neonates, and significantly less so between humans and macaques. The premotor-parietal rsFC had most significant contribution to the formation of the neonatal tool network. These results suggest that an intrinsic brain network potentially supporting tool processing exists in the human brain prior to individual tool use experiences, and that the premotor-parietal functional connection in particular offers a brain basis for complex tool behaviors specific to humans.

Details DOI

NeurIPS Conference 2021 Conference Paper

Adversarial Reweighting for Partial Domain Adaptation

Xiang Gu
Xi Yu
Yan Yang
Jian Sun
Zongben Xu

Partial domain adaptation (PDA) has gained much attention due to its practical setting. The current PDA methods usually adapt the feature extractor by aligning the target and reweighted source domain distributions. In this paper, we experimentally find that the feature adaptation by the reweighted distribution alignment in some state-of-the-art PDA methods is not robust to the ``noisy'' weights of source domain data, leading to negative domain transfer on some challenging benchmarks. To tackle the challenge of negative domain transfer, we propose a novel Adversarial Reweighting (AR) approach that adversarially learns the weights of source domain data to align the source and target domain distributions, and the transferable deep recognition network is learned on the reweighted source domain data. Based on this idea, we propose a training algorithm that alternately updates the parameters of the network and optimizes the weights of source domain data. Extensive experiments show that our method achieves state-of-the-art results on the benchmarks of ImageNet-Caltech, Office-Home, VisDA-2017, and DomainNet. Ablation studies also confirm the effectiveness of our approach.

PDF Details

AAAI Conference 2021 Conference Paper

Measuring Dependence with Matrix-based Entropy Functional

Shujian Yu
Francesco Alesiani
Xi Yu
Robert Jenssen
Jose Principe

Measuring the dependence of data plays a central role in statistics and machine learning. In this work, we summarize and generalize the main idea of existing information-theoretic dependence measures into a higher-level perspective by the Shearer’s inequality. Based on our generalization, we then propose two measures, namely the matrix-based normalized total correlation and the matrix-based normalized dual total correlation, to quantify the dependence of multiple variables in arbitrary dimensional space, without explicit estimation of the underlying data distributions. We show that our measures are differentiable and statistically more powerful than prevalent ones. We also show the impact of our measures in four different machine learning problems, namely the gene regulatory network inference, the robust machine learning under covariate shift and non-Gaussian noises, the subspace outlier detection, and the understanding of the learning dynamics of convolutional neural networks, to demonstrate their utilities, advantages, as well as implications to those problems.

PDF Details

IS Journal 2020 Journal Article

Data Cleaning for Personal Credit Scoring by Utilizing Social Media Data: An Empirical Study

Xi Yu
Qi Yang
Ruiqi Wang
Runqing Fang
Mingsen Deng

With the accumulation of data on personal behavior and the development of machine learning models and algorithms, it is becoming possible to use social media data for personal credit scoring. In this article, we use the systematic sampling method to obtain Douban's social media data. Because there are many abnormal users in these data, they are “real but false data” for personal credit evaluation. In order to better carry out personal credit scoring, we propose three criteria, power exponents of time interval distribution of individual user $\gamma _i$γi, user activity $A_i$Ai, and the ratio of out-degree and in-degree $R_i$Ri of user $i$i, which are used to systematically clean the data. And then, we used the logistic regression method to score the individual credits of users before and after data cleaning, and found that the rank order of personal credit scoring has changed significantly. This change is largely attributed to the changes of network structure after data cleaning. We believe that our work is very important to use the social media data to establish a credible personal credit evaluation system to reduce the credit risk of the current Internet financial industry.

Details DOI

YNIMG Journal 2011 Journal Article

Dissociative neural correlates of semantic processing of nouns and verbs in Chinese — A language with minimal inflectional morphology

Xi Yu
Sam Po Law
Zaizhu Han
Caozhe Zhu
Yanchao Bi

Numerous studies using various techniques and methodologies have demonstrated distinctive responses to nouns and verbs both at the behavioral and neurological levels. However, since the great majority of these studies involved tasks employing pictorial stimuli and languages with rich inflectional morphology, it is not clear whether word class effects resulted from semantic differences between objects and actions or different inflectional operations associated with the two word classes. Such shortcomings were addressed in this study by using a language with impoverished inflectional morphology — Chinese. Both concrete and abstract words were included, while controlling for nuisance variables between the two word classes, including imageability, word frequency, age-of-acquisition, and number of stroke. Participants were asked to judge the semantic relatedness of noun or verb pairs by pressing different buttons. The results revealed specific neural correlates for verb class in left lateral temporal and inferior frontal regions. Furthermore, the patterns of neural distribution of nouns and verbs were consistent with observations from Indo-European languages. Plausible accounts for neural separation of word classes were considered.

Details DOI