Flexible Affinity Matrix Learning for Unsupervised and Semisupervised Classification.

Robust structure-preservation tensorized representation for multi-view unsupervised feature selection.

Clustering is an unsupervised learning approach that explores data and seeks groups of similar objects. Many classical clustering models such as k-means and DBSCAN are based on heuristics algorithms and suffer from local optimal solutions and numerical instability. Recently convex clustering has received increasing attentions, which leverages the sparsity inducing norms and enjoys many attractive theoretical properties. However, convex clustering is based on Euclidean distance and is thus not robust against outlier features. Since the outlier features are very common especially when dimensionality is high, the vulnerability has greatly limited the applicability of convex clustering to analyze many real-world datasets. In this paper, we address the challenge by proposing a novel robust convex clustering method that simultaneously performs convex clustering and identifies outlier features. Specifically, the proposed method learns to decompose the data matrix into a clustering structure component and a group sparse component that captures feature outliers. We develop a block coordinate descent algorithm which iteratively performs convex clustering after outliers features are identified and eliminated. We also propose an efficient algorithm for solving the convex clustering by exploiting the structures on its dual problem. Moreover, to further illustrate the statistical stability, we present the theoretical performance bound of the proposed clustering method. Empirical studies on synthetic data and real-world data demonstrate that the proposed robust convex clustering can detect feature outliers as well as improve cluster quality.

The process of merging data of different data sources is referred to as record linkage. A medical environment with increased preconditions on privacy protection demands the transformation of clear-text attributes like first name or date of birth into one-way encrypted pseudonyms. When performing an automated or privacy preserving record linkage there might be the need of a binary classification deciding whether two records should be classified as the same entity. The classification is the final of the four main phases of the record linkage process: Preprocessing, indexing, matching and classification. The choice of binary classification techniques in dependence of project specifications in particular data quality has not extensively been studied yet. The aim of this work is the introduction and evaluation of an automatable semi-supervised binary classification system applied within the field of record linkage capable of competing or even surpassing advanced automated techniques of the domain of unsupervised classification. This work describes the rationale leading to the model and the final implementation of an automatable semi-supervised binary classification system and the comparison of its classification performance to an advanced active learning approach out of the domain of unsupervised learning. The performance of both systems has been measured on a broad variety of artificial test sets (n = 400), based on real patient data, with distinct and unique characteristics. While the classification performance for both methods measured as F-measure was relatively close on test sets with maximum defined data quality, 0.996 for semi-supervised classification, 0.993 for unsupervised classification, it incrementally diverged for test sets of worse data quality dropping to 0.964 for semi-supervised classification and 0.803 for unsupervised classification. Aside from supplying a viable model for semi-supervised classification for automated probabilistic record linkage, the tests conducted on a large amount of test sets suggest that semi-supervised techniques might generally be capable of outperforming unsupervised techniques especially on data with lower levels of data quality.

The research on complex networks has achieved significant progress in revealing the mesoscopic features of networks. Community detection is an important aspect of understanding real-world complex systems. We present in this paper a High-order node proximity Spectral Clustering on Ratios-of-Eigenvectors (SCOREH+) algorithm for locating communities in complex networks. The algorithm improves SCORE and SCORE+ and preserves high-order transitivity information of the network affinity matrix. We optimize the high-order proximity matrix from the initial affinity matrix using the Radial Basis Functions (RBFs) and Katz index. In addition to the optimization of the Laplacian matrix, we implement a procedure that joins an additional eigenvector (the (k + 1)th leading eigenvector) to the spectrum domain for clustering if the network is considered to be a “weak signal” graph. The algorithm has been successfully applied to both real-world and synthetic data sets. The proposed algorithm is compared with state-of-art algorithms, such as ASE, Louvain, Fast-Greedy, Spectral Clustering (SC), SCORE, and SCORE+. To demonstrate the high efficacy of the proposed method, we conducted comparison experiments on eleven real-world networks and a number of synthetic networks with noise. The experimental results in most of these networks demonstrate that SCOREH+ outperforms the baseline methods. Moreover, by tuning the RBFs and their shaping parameters, we may generate state-of-the-art community structures on all real-world networks and even on noisy synthetic networks.

Infinity Laplacian on graphs with gradient terms for image and data clustering

Condition monitoring of road surfaces has acquired a lot of attention in the field of computer vision throughout the years. It is due to two main reasons; firstly, it produces safety and comfort to the community, and secondly, it causes less damage to the vehicles for an advanced driver assistance system (ADAS). To this extent, this article aims to present a real-time vision-based approach that automatically segments the road anomalies from the drivable area. An Intel RealSense D435 depth camera has been employed to capture RGB and depth (RGB-D) images of the road surface. An unsupervised learning method based on diffusion process has been employed to learn the affinity matrix of the RGB-D data and spectral clustering has been applied on the updated affinity matrix to cluster the road images. Image multiplex visibility graphs of the input sensor data are diffused by regularized diffusion process (RDP) to update the affinity matrix followed by generation of saliency map of the road surfaces. The prime motive to employ RDP is to use the graph Laplacian as a tool for similarity measurement for preserving the manifold structure. Qualitative and quantitative results reveal the efficacy of the proposed system with state-of-the-art methods on our RGB-D dataset. Benchmark datasets (KITTI and Cityscapes) are also used to validate the proposed method for segmentation of the drivable area for an intelligent transportation system.

Detecting multimodal misinformation, especially in the form of image-text pairs, is crucial.Obtaining large-scale, high-quality real-world fact-checking datasets for training detectors is costly, leading researchers to use synthetic datasets generated by AI technologies.However, the generalizability of detectors trained on synthetic data to real-world scenarios remains unclear due to the distribution gap.To address this, we propose learning from synthetic data for detecting real-world multimodal misinformation through two model-agnostic data selection methods that match synthetic and real-world data distributions.Experiments show that our method enhances the performance of a small MLLM (13B) on real-world fact-checking datasets, enabling it to even surpass GPT-4V (OpenAI, 2023b).

In perception tasks of automated vehicles (AVs) data-driven have often outperformed conventional approaches. This motivated us to develop a data-driven methodology to compute occupancy grid maps (OGMs) from lidar measurements. Our approach extends previous work such that the estimated environment representation now contains an additional layer for cells occupied by dynamic objects. Earlier solutions could only distinguish between free and occupied cells. The information whether an obstacle could move plays an important role for planning the behavior of an AV. We present two approaches to generating training data. One approach extends our previous work on using synthetic training data so that OGMs with the three aforementioned cell states are generated. The other approach uses manual annotations from the nuScenes [1] dataset to create training data. We compare the performance of both models in a quantitative analysis on unseen data from the real-world dataset. Next, we analyze the ability of both approaches to cope with a domain shift, i.e. when presented with lidar measurements from a different sensor on a different vehicle. We propose using information gained from evaluation on real-world data to further close the reality gap and create better synthetic data that can be used to train occupancy grid mapping models for arbitrary sensor configurations. Code is available at https://github.com/ika-rwth-aachen/DEviLOG.

Subspace clustering groups a set of samples from a union of several linear subspaces into clusters, so that the samples in the same cluster are drawn from the same linear subspace. In the majority of the existing work on subspace clustering, clusters are built based on feature information, while sample correlations in their original spatial structure are simply ignored. Besides, original high-dimensional feature vector contains noisy/redundant information, and the time complexity grows exponentially with the number of dimensions. To address these issues, we propose a tensor low-rank representation (TLRR) and sparse coding-based (TLRRSC) subspace clustering method by simultaneously considering feature information and spatial structures. TLRR seeks the lowest rank representation over original spatial structures along all spatial directions. Sparse coding learns a dictionary along feature spaces, so that each sample can be represented by a few atoms of the learned dictionary. The affinity matrix used for spectral clustering is built from the joint similarities in both spatial and feature spaces. TLRRSC can well capture the global structure and inherent feature information of data and provide a robust subspace segmentation from corrupted data. Experimental results on both synthetic and real-world data sets show that TLRRSC outperforms several established stateof- the-art methods.

The block diagonal structure of an affinity matrix is a commonly desired property in cluster analysis because it represents clusters of feature vectors by non-zero coefficients that are concentrated in blocks. However, recovering a block diagonal affinity matrix is challenging in real-world applications, in which the data may be subject to outliers and heavy-tailed noise that obscure the hidden cluster structure. To address this issue, we first analyze the effect of different fundamental outlier types in graph-based cluster analysis. A key idea that simplifies the analysis is to introduce a vector that represents a block diagonal matrix as a piece-wise linear function of the similarity coefficients that form the affinity matrix. We reformulate the problem as a robust piece-wise linear fitting problem and propose a Fast and Robust Sparsity-Aware Block Diagonal Representation (FRS-BDR) method, which jointly estimates cluster memberships and the number of blocks. Comprehensive experiments on a variety of real-world applications demonstrate the effectiveness of FRS-BDR in terms of clustering accuracy, robustness against corrupted features, computation time and cluster enumeration performance.

Multi-task learning (MTL) methods have shown promising performance by learning multiple relevant tasks simultaneously, which exploits to share useful information across relevant tasks. Among various MTL methods, clustered multi-task learning (CMTL) assumes that all tasks can be clustered into groups and attempts to learn the underlying cluster structure from the training data. In this paper, we present a new approach for CMTL, called flexible clustered multi-task (FCMTL), in which the cluster structure is learned by identifying representative tasks. The new approach allows an arbitrary task to be described by multiple representative tasks, effectively soft-assigning a task to multiple clusters with different weights. Unlike existing counterpart, the proposed approach is more flexible in that (a) it does not require clusters to be disjoint, (b) tasks within one particular cluster do not have to share information to the same extent, and (c) the number of clusters is automatically inferred from data. Computationally, the proposed approach is formulated as a row-sparsity pursuit problem. We validate the proposed FCMTL on both synthetic and real-world data sets, and empirical results demonstrate that it outperforms many existing MTL methods.

Red teaming is a common cybersecurity practice that simulates real-world adversarial cyber operations on defended systems to identify vulnerabilities. Current red team tools often have limited logging capabilities, resulting in insufficient analysis that prevents red teams from receiving real-time feedback and insights after operations. The application of machine learning for automating the analysis of red team operations is severely constrained by the scarcity of labeled, real-world log data. This research addresses this challenge by exploring the potential of using synthetic data to train attack-detection models for Cobalt Strike logs. We systematically evaluate three different training approaches for analyzing Cobalt Strike operational logs: synthetic-only, real-world-only, and a hybrid approach that combines both data types. Our methodology employs a comprehensive feature engineering pipeline that includes both programmatic log generation for creating large-scale structured data and large language model techniques for introducing variety and edge cases. We transform each log file into a high-dimensional vector that includes event types, command verbs, temporal activity patterns, and mappings to the MITRE ATT&CK knowledge base. Random Forest classification models are trained using this feature set to distinguish between successful and failed attack scenarios. By rigorously testing each training approach against a manually labeled ground-truth set of 112 authentic Cobalt Strike logs, we quantify the performance and limitations of each strategy. Our main contribution is demonstrating that a hybrid training strategy achieves 94% accuracy, greatly surpassing synthetic-only models (56%) and real-world-only models (79%). This combined approach effectively addresses both the domain gap in synthetic data and the data scarcity in small, real-world datasets. The hybrid model learns attack diversity from over 30,000 synthetic scenarios while grounding understanding in the authentic structural patterns of real logs, providing a 15 percentage-point improvement over real-data-only approaches. This research offers a practical framework for enhancing limited real-world cybersecurity datasets by strategically integrating synthetic data, enabling immediate use in Department of Defense red team operations and wider cybersecurity machine learning applications.

Multi-view data clustering often aims to utilize various representations or views of original data to improve the clustering performance compared to the single-view clustering approach. Most multi-view subspace clustering methods are proposed to construct the affinity matrix of each view individually and then implement with spectral clustering for multi-view data clustering. The multi-view low-rank sparse subspace clustering (MLRSSC) is an effective and popular clustering algorithm among multi-view subspace clustering. This method can explore the joint subspace representation through creating an affinity matrix integrated of all views of input data. In addition, the low-rank and sparsity constraints are introduced into this method to enhance the clustering results. However, the original MLRSSC uses the mean square error as the fidelity term while not consider the complex noise pollution in real situations. Therefore, we introduce a complex noise modeling approach, i.e., independent and piecewise identically distributed (IPID) noise model, for MLRSSC to improve its performance. The related experimental results confirm that this proposed algorithm surpasses many state-of-the-art subspace clustering methods on several real-world datasets.

To assess the validity of privacy-preserving synthetic data by comparing results from synthetic versus original EHR data analysis. A published retrospective cohort study on real-world effectiveness of COVID-19 vaccines by Maccabi Healthcare Services in Israel was replicated using synthetic data generated from the same source, and the results were compared between synthetic versus original datasets. The endpoints included COVID-19 infection, symptomatic COVID-19 infection and hospitalization due to infection and were also assessed in several demographic and clinical subgroups. In comparing synthetic versus original data estimates, several metrices were utilized: standardized mean differences (SMD), decision agreement, estimate agreement, confidence interval overlap, and Wald test. Synthetic data were generated five times to assess the stability of results. The distribution of demographic and clinical characteristics demonstrated very small difference (< 0.01 SMD). In the comparison of vaccine effectiveness assessed in relative risk reduction between synthetic versus original data, there was a 100% decision agreement, 100% estimate agreement, and a high level of confidence interval overlap (88.7%-99.7%) in all five replicates across all subgroups. Similar findings were achieved in the assessment of vaccine effectiveness against symptomatic COVID-19 Infection. In the comparison of hazard ratios for COVID 19-related hospitalization and odds ratio for symptomatic COVID-19 Infection, the Wald tests suggested no significant difference between respective effect estimates in all five replicates for all patient subgroups but there were disagreements in estimate and decision metrices in some subgroups and replicates. Overall, comparison of synthetic versus original real-world data demonstrated good validity and reliability. Transparency on the process to generate high fidelity synthetic data and assurances of patient privacy are warranted.

Feature selection is an important pre-processing stage in many machine learning and pattern recognition tasks, which eliminates irrelevant and redundant features and improves learning performance. Regularized sparse feature selection methods like Lasso and its variants using l 1 -norm regularization term in their optimization problem have received much attention in recent years. Prior information could be represented as the class labels or pairwise constraints, i.e., must-link (positive) and cannot-link (negative) constraints. In this paper, besides the l 1 -norm regularization term, a normalized adapted affinity matrix is applied to embed the pairwise constraints in the affinity matrix. In the proposed affinity matrix, the weights are strengthened/weakened according to the positive/negative constraints. The experimental results on several data sets from University of California-Irvine (UCI) machine learning repository and a high dimensional data set, show the effectiveness of the proposed method in the classification tasks compared to some similar feature selection methods.