我们提出“碰撞交叉熵”，作为香农交叉熵（CE）损失的一种稳健替代方案，适用于类别标签由软类别分布 y 表示的情形。一般而言，软标签能够自然地表示分类中的模糊目标。它们对于自标记聚类方法尤为重要，因为在这些方法中，潜在伪标签与模型参数联合估计，并且不确定性普遍存在。在软标签情况下，香农交叉熵会教导模型预测复现每个训练样本中的不确定性，这会抑制模型从这些样本中学习和泛化的能力。作为替代损失，我们提出“碰撞概率”的负对数，该概率最大化两个随机变量——预测类别与未知真实类别——相等的机会。我们证明它具有广义交叉熵的性质。所提出的碰撞交叉熵在独热标签下与香农交叉熵一致，但在软标签下的训练行为不同。例如，与香农交叉熵不同，当 y 为均匀分布时，数据点对训练的贡献为零。碰撞交叉熵显著改善了由软不确定目标监督的分类。与香农交叉熵不同，碰撞交叉熵对 y 和网络预测是对称的，这在自标记聚类中两个分布都被估计的背景下尤为重要。聚焦于以自标记和基于熵的损失为主导的判别式深度聚类，我们表明使用碰撞交叉熵能够提升当前最先进水平。我们还推导出一种高效的 EM 算法，显著加速了使用碰撞交叉熵的伪标签估计。
英文摘要：
We propose "collision cross-entropy" as a robust alternative to Shannon's cross-entropy (CE) loss when class labels are represented by soft categorical distributions y. In general, soft labels can naturally represent ambiguous targets in classification. They are particularly relevant for self-labeled clustering methods, where latent pseudo-labels are jointly estimated with the model parameters and uncertainty is prevalent. In case of soft labels, Shannon's CE teaches the model predictions to reproduce the uncertainty in each training example, which inhibits the model's ability to learn and generalize from these examples. As an alternative loss, we propose the negative log of "collision probability" that maximizes the chance of equality between two random variables, predicted class and unknown true class. We show that it has the properties of a generalized CE. The proposed collision CE agrees with Shannon's CE for one-hot labels, but the training from soft labels differs. For example, unlike Shannon's CE, data points where y is a uniform distribution have zero contribution to the training. Collision CE significantly improves classification supervised by soft uncertain targets. Unlike Shannon's, collision CE is symmetric for y and network predictions, which is particularly relevant when both distributions are estimated in the context of self-labeled clustering. Focusing on discriminative deep clustering where self-labeling and entropy-based losses are dominant, we show that the use of collision CE improves the state-of-the-art. We also derive an efficient EM algorithm that significantly speeds up the pseudo-label estimation with collision CE.
University of Oxford（牛津大学）；Universidade Federal Rural de Pernambuco（伯南布哥联邦农村大学）；Otto-von-Guericke-Universität Magdeburg（马格德堡奥托·冯·格里克大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）；University of Surrey（萨里大学）
We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to non-severe label noise problems, in comparison to the state of the art (SOTA) methods. ScanMix is based on the expectation maximisation framework, where the E-step estimates the latent variable to cluster the training images based on their appearance and classification results, and the M-step optimises the SSL classification and learns effective feature representations via semantic clustering. We pres…
Inception Institute of Artificial Intelligence（初始人工智能研究院）；University of Macau（澳门大学）；Terminus Group（特斯联集团）
The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it often suffers from label inconsistency or limited diversity, which leads to poor performance. In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space. We address this by minimizing the inter- to intra-class similarity ratio to provide clustering-friendly embedding features, and validate our approach t…
An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering
State Key Laboratory for Novel Software Technology, Nanjing University（新型软件技术国家重点实验室，南京大学）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Few-shot learning is challenging due to its very limited data and labels. Recent studies in big transfer (BiT) show that few-shot learning can greatly benefit from pretraining on large scale labeled dataset in a different domain. This paper asks a more challenging question: "can we use as few as possible labels for few-shot learning in both pretraining (with no labels) and fine-tuning (with fewer labels)?". Our key insight is that the clustering of target samples in the feature space is all we need for few-shot finetuning. It explains why the vanilla unsupervised pretraining (poor clustering) …
Deep neural networks (DNNs) offer a means of addressing the challenging task of clustering high-dimensional data. DNNs can extract useful features, and so produce a lower dimensional representation, which is more amenable to clustering techniques. As clustering is typically performed in a purely unsupervised setting, where no training labels are available, the question then arises as to how the DNN feature extractor can be trained. The most accurate existing approaches combine the training of the DNN with the clustering objective, so that information from the clustering process can be used to …
Cross-Modality Clustering-based Self-Labeling for Multimodal Data Classification
Faculty of Information；Communication Technology Wrocław University of Science；School of Computer Science University of Birmingham Birmingham, United Kingdom
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）；A*STAR（新加坡科技研究局）
Joint clustering and feature learning methods have shown remarkable performance in unsupervised representation learning. However, the training schedule alternating between feature clustering and network parameters update leads to unstable learning of visual representations. To overcome this challenge, we propose Online Deep Clustering (ODC) that performs clustering and network update simultaneously rather than alternatingly. Our key insight is that the cluster centroids should evolve steadily in keeping the classifier stably updated. Specifically, we design and maintain two dynamic memory modu…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）
Unsupervised pretraining has achieved great success and many recent works have shown unsupervised pretraining can achieve comparable or even slightly better transfer performance than supervised pretraining on downstream target datasets. But in this paper, we find this conclusion may not hold when the target dataset has very few labeled samples for finetuning, \ie, few-label transfer. We analyze the possible reason from the clustering perspective: 1) The clustering quality of target samples is of great importance to few-label transfer; 2) Though contrastive learning is essential to learn how to…
Multi-label Classification via Adaptive Resonance Theory-based Clustering
Graduate School of Engineering, Osaka Prefecture University（大阪府立大学工学院）；Faculty of Computer Science and Information Technology, University of Malaya（马来亚大学计算机科学与信息技术学院）；Southern University of Science and Technology（南方科技大学）
ANIMC: A Soft Framework for Auto-weighted Noisy and Incomplete Multi-view Clustering
Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology（大数据安全湖北工程研究中心，信息科学与工程学院，华中科技大学）；School of Computer Science and Technology, Huazhong University of Science and Technology（计算机科学与技术学院，华中科技大学）；Key Laboratory of Information Storage System Ministry of Education of China, Huazhong University of Science and Technology（信息存储系统教育部重点实验室，华中科技大学）；Department of Electrical and Computer Engineering, University of Florida（电气与计算机工程系，佛罗里达大学）
Yale University（耶鲁大学）；Massachusetts Institute of Technology（麻省理工学院）；University of California, Irvine（加州大学欧文分校）
In the era of single-cell sequencing, there is a growing need to extract insights from data with clustering methods. Here, we introduce Forest Fire Clustering, an efficient and interpretable method for cell-type discovery from single-cell data. Forest Fire Clustering makes minimal prior assumptions and, different from current approaches, calculates a non-parametric posterior probability that each cell is assigned a cell-type label. These posterior distributions allow for the evaluation of a label confidence for each cell and enable the computation of "label entropies," highlighting transitions…
TCG Crest Kolkata, India（印度加尔各答TCG Crest）；School of Computer Science, University College Dublin, Ireland（爱尔兰都柏林大学学院计算机科学学院）；Indian Statistical Institute Kolkata, India（印度统计研究所加尔各答分所）
There is often a mixture of very frequent labels and very infrequent labels in multi-label datatsets. This variation in label frequency, a type class imbalance, creates a significant challenge for building efficient multi-label classification algorithms. In this paper, we tackle this problem by proposing a minority class oversampling scheme, UCLSO, which integrates Unsupervised Clustering and Label-Specific data Oversampling. Clustering is performed to find out the key distinct and locally connected regions of a multi-label dataset (irrespective of the label information). Next, for each label,…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of Minnesota（明尼苏达大学）
Creating separable representations via representation learning and clustering is critical in analyzing large unstructured datasets with only a few labels. Separable representations can lead to supervised models with better classification capabilities and additionally aid in generating new labeled samples. Most unsupervised and semisupervised methods to analyze large datasets do not leverage the existing small amounts of labels to get better representations. In this paper, we propose a spatiotemporal clustering paradigm that uses spatial and temporal features combined with a constrained loss to…
Technical University of Munich（慕尼黑工业大学）；Massachusetts Eye and Ear Hospital（马萨诸塞眼耳医院）；Harvard Medical School（哈佛医学院）；LMU Munich（慕尼黑大学）
We propose a Deep Variational Clustering (DVC) framework for unsupervised representation learning and clustering of large-scale medical images. DVC simultaneously learns the multivariate Gaussian posterior through the probabilistic convolutional encoder and the likelihood distribution with the probabilistic convolutional decoder; and optimizes cluster labels assignment. Here, the learned multivariate Gaussian posterior captures the latent distribution of a large set of unlabeled images. Then, we perform unsupervised clustering on top of the variational latent space using a clustering loss. In …
Clustering of Time-Varying Graphs Based on Temporal Label Smoothness
Tokyo University of Agriculture and Technology（东京农工大学）；Tokyo University of Science（东京理科大学）；Osaka University（大阪大学）；The Chinese University of Hong Kong（香港中文大学）
The performance of supervised classification techniques often deteriorates when the data has noisy labels. Even the semi-supervised classification approaches have largely focused only on the problem of handling missing labels. Most of the approaches addressing the noisy label data rely on deep neural networks (DNN) that require huge datasets for classification tasks. This poses a serious challenge especially in process and manufacturing industries, where the data is limited and labels are noisy. We propose a semi-supervised cascaded clustering (SSCC) algorithm to extract patterns and generate …
Although data-driven fault diagnosis methods have been widely applied, massive labeled data are required for model training. However, a difficulty of implementing this in real industries hinders the application of these methods. Hence, an effective diagnostic approach that can work well in such situation is urgently needed.In this study, a multi-stage semi-supervised improved deep embedded clustering (MS-SSIDEC) method, which combines semi-supervised learning with improved deep embedded clustering (IDEC), is proposed to jointly explore scarce labeled data and massive unlabeled data. In the fir…
Shandong Normal University（山东师范大学）；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东计算机科学中心（国家超级计算济南中心））；Shandong Artificial Intelligence Institute（山东人工智能研究院）；University of Electronic Science and Technology of China（电子科技大学）；San Diego State University（圣地亚哥州立大学）
The existing person search methods use the annotated labels of person identities to train deep networks in a supervised manner that requires a huge amount of time and effort for human labeling. In this paper, we first introduce a novel framework of person search that is able to train the network in the absence of the person identity labels, and propose efficient unsupervised clustering methods to substitute the supervision process using annotated person identity labels. Specifically, we propose a hard negative mining scheme based on the uniqueness property that only a single person has the sam…
Node classification on graphs is an important task in many practical domains. It usually requires labels for training, which can be difficult or expensive to obtain in practice. Given a budget for labelling, active learning aims to improve performance by carefully choosing which nodes to label. Previous graph active learning methods learn representations using labelled nodes and select some unlabelled nodes for label acquisition. However, they do not fully utilize the representation power present in unlabelled nodes. We argue that the representation power in unlabelled nodes can be useful for …
University of Oxford（牛津大学）；Alan Turing Institute（艾伦·图灵研究所）
In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the case that some classes of data are found only in the unlabelled dataset -- perhaps the labelling process was biased -- so we do not have any labelled examples to train on for some classes. We call this learning regime $\textit{semi-unsupervised learning}$, an extreme case of semi-supervised learning, where some classes have no labelled exemplars in the train…
Movie genre classification is an active research area in machine learning. However, due to the limited labels available, there can be large semantic variations between movies within a single genre definition. We expand these 'coarse' genre labels by identifying 'fine-grained' semantic information within the multi-modal content of movies. By leveraging pre-trained 'expert' networks, we learn the influence of different combinations of modes for multi-label genre classification. Using a contrastive loss, we continue to fine-tune this 'coarse' genre classification network to identify high-level in…
Fuzhou University（福州大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
In this work, we study the problem of partitioning a set of graphs into different groups such that the graphs in the same group are similar while the graphs in different groups are dissimilar. This problem was rarely studied previously, although there have been a lot of work on node clustering and graph classification. The problem is challenging because it is difficult to measure the similarity or distance between graphs. One feasible approach is using graph kernels to compute a similarity matrix for the graphs and then performing spectral clustering, but the effectiveness of existing graph ke…
Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods and introduce a new method called Heatmap Clustering. There, we apply a $k$-means clustering algorithm on heatmaps produced by the state-of-the-art explainable AI method Layer-wise relevance propagation. The goal is to separate poisoned from un-poisoned data in the dataset. We compare this method with a similar method, called Activation Clustering, which also uses $k$-means clustering but applies it on the activation…
Non-IID dataset and heterogeneous environment of the local clients are regarded as a major issue in Federated Learning (FL), causing a downturn in the convergence without achieving satisfactory performance. In this paper, we propose a novel Label-wise clustering algorithm that guarantees the trainability among geographically dispersed heterogeneous local clients, by selecting only the local models trained with a dataset that approximates into uniformly distributed class labels, which is likely to obtain faster minimization of the loss and increment the accuracy among the FL network. Through co…
Gene annotation addresses the problem of predicting unknown associations between gene and functions (e.g., biological processes) of a specific organism. Despite recent advances, the cost and time demanded by annotation procedures that rely largely on in vivo biological experiments remain prohibitively high. This paper presents a novel in silico approach for to the annotation problem that combines cluster analysis and hierarchical multi-label classification (HMC). The approach uses spectral clustering to extract new features from the gene co-expression network (GCN) and enrich the prediction ta…
