Community detection is one of the most important methodological fields of network science, and one which has attracted a significant amount of attention over the past decades. This area deals with the automated division of a network into fundamental building blocks, with the objective of providing a summary of its large-scale structure. Despite its importance and widespread adoption, there is a noticeable gap between what is arguably the state-of-the-art and the methods that are actually used in practice in a variety of fields. Here we attempt to address this discrepancy by dividing existing methods according to whether they have a "descriptive" or an "inferential" goal. While descriptive methods find patterns in networks based on context-dependent notions of community structure, inferential methods articulate generative models, and attempt to fit them to data. In this way, they are able to provide insights into the mechanisms of network formation, and separate structure from randomness in a manner supported by statistical evidence. We review how employing descriptive methods with inferential aims is riddled with pitfalls and misleading answers, and thus should be in general avoided. We argue that inferential methods are more typically aligned with clearer scientific questions, yield more robust results, and should be in many cases preferred. We attempt to dispel some myths and half-truths often believed when community detection is employed in practice, in an effort to improve both the use of such methods as well as the interpretation of their results.
Recovering and distinguishing between the strict-preference, indifference and/or indecisiveness parts of a decision maker's preferences is a challenging task but also important for testing theory and conducting welfare analysis. This paper contributes towards this goal by reporting on data from a lab experiment on riskless choice that were analyzed with novel theory-guided computational methods. The experiment included both Forced- and Free-Choice treatments. Its primary novelty consisted of allowing all subjects to select multiple alternatives at each menu. Based on a non-parametric goodness-of-fit criterion that we introduce, which generalizes intuitively a widely used pre-existing method to environments of multi-valued choices, each subjects' decision data were tested against three structured general-choice models that feature maximization of stable but potentially weak and/or incomplete preferences. Nearly 60% of all subjects' are well-explained by one of these models, typically with a unique model-optimal preference relation per subject. Importantly, preferences usually (80%) had a non-trivial indifference part and, where applicable, a clearly distinct indecisiveness part. The achieved uncoupling of revealed indifference and indecisiveness is documented empirically for the first time.
Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of generating caption given an image. In this work, we repurpose such models to generate a descriptive text given an image at inference time, without any further training or tuning steps. This is done by combining the visual-semantic model with a large language model, benefiting from the knowledge in both web-scale models. The resulting captions are much less restrictive than those obtained by supervised captioning methods. Moreover, as a zero-shot learning method, it is extremely flexible and we demonstrate its ability to perform image arithmetic in which the inputs can be either images or text, and the output is a sentence. This enables novel high-level vision capabilities such as comparing two images or solving visual analogy tests. Our code is available at: https://github.com/YoadTew/zero-shot-image-to-text.
This paper addresses the task of generating fluent descriptions by training on a non-uniform combination of data sources, containing both human-annotated and web-collected captions. Large-scale datasets with noisy image-text pairs, indeed, provide a sub-optimal source of supervision because of their low-quality descriptive style, while human-annotated datasets are cleaner but smaller in scale. To get the best of both worlds, we propose to leverage and separate semantics and descriptive style through the incorporation of a style token and keywords extracted through a retrieval component. The proposed model avoids the need of object detectors, is trained with a single objective of prompt language modeling, and can replicate the style of human-collected captions while training on sources with different input styles. Experimentally, the model shows a strong capability of recognizing real-world concepts and producing high-quality captions. Extensive experiments are performed on different image captioning datasets, including CC3M, nocaps, and the competitive COCO dataset, where our model consistently outperforms baselines and state-of-the-art approaches.
Security risk assessment and prediction are critical for organisations deploying Internet of Things (IoT) devices. An absolute minimum requirement for enterprises is to verify the security risk of IoT devices for the reported vulnerabilities in the National Vulnerability Database (NVD). This paper proposes a novel risk prediction for IoT devices based on publicly available information about them. Our solution provides an easy and cost-efficient solution for enterprises of all sizes to predict the security risk of deploying new IoT devices. After an extensive analysis of the NVD records over the past eight years, we have created a unique, systematic, and balanced dataset for vulnerable IoT devices, including key technical features complemented with functional and descriptive features available from public resources. We then use machine learning classification models such as Gradient Boosting Decision Trees (GBDT) over this dataset and achieve 71% prediction accuracy in classifying the severity of device vulnerability score.
Medical image data are usually imbalanced across different classes. One-class classification has attracted increasing attention to address the data imbalance problem by distinguishing the samples of the minority class from the majority class. Previous methods generally aim to either learn a new feature space to map training samples together or to fit training samples by autoencoder-like models. These methods mainly focus on capturing either compact or descriptive features, where the information of the samples of a given one class is not sufficiently utilized. In this paper, we propose a novel deep learning-based method to learn compact features by adding constraints on the bottleneck features, and to preserve descriptive features by training an autoencoder at the same time. Through jointly optimizing the constraining loss and the autoencoder's reconstruction loss, our method can learn more relevant features associated with the given class, making the majority and minority samples more distinguishable. Experimental results on three clinical datasets (including the MRI breast images, FFDM breast images and chest X-ray images) obtains state-of-art performance compared to previous methods.
In this article, we show and discuss the results of a quantitative and qualitative analysis of open citations to retracted publications in the humanities domain. Our study was conducted by selecting retracted papers in the humanities domain and marking their main characteristics (e.g., retraction reason). Then, we gathered the citing entities and annotated their basic metadata (e.g., title, venue, subject, etc.) and the characteristics of their in-text citations (e.g., intent, sentiment, etc.). Using these data, we performed a quantitative and qualitative study of retractions in the humanities, presenting descriptive statistics and a topic modeling analysis of the citing entities' abstracts and the in-text citation contexts. As part of our main findings, we noticed that there was no drop in the overall number of citations after the year of retraction, with few entities which have either mentioned the retraction or expressed a negative sentiment toward the cited publication. In addition, on several occasions, we noticed a higher concern/awareness when it was about citing a retracted publication, by the citing entities belonging to the health sciences domain, if compared to the humanities and the social science domains. Philosophy, arts, and history are the humanities areas that showed the higher concern toward the retraction.
Machine-in-the-loop writing aims to enable humans to collaborate with models to complete their writing tasks more effectively. Prior work has found that providing humans a machine-written draft or sentence-level continuations has limited success since the generated text tends to deviate from humans' intention. To allow the user to retain control over the content, we train a rewriting model that, when prompted, modifies specified spans of text within the user's original draft to introduce descriptive and figurative elements locally in the text. We evaluate the model on its ability to collaborate with humans on the task of creative image captioning. On a user study through Amazon Mechanical Turk, our model is rated to be more helpful than a baseline infilling language model. In addition, third-party evaluation shows that users write more descriptive and figurative captions when collaborating with our model compared to completing the task alone.
The magnitude of a finite metric space has recently emerged as a novel invariant quantity, allowing to measure the effective size of a metric space. Despite encouraging first results demonstrating the descriptive abilities of the magnitude, such as being able to detect the boundary of a metric space, the potential use cases of magnitude remain under-explored. In this work, we investigate the properties of the magnitude on images, an important data modality in many machine learning applications. By endowing each individual images with its own metric space, we are able to define the concept of magnitude on images and analyse the individual contribution of each pixel with the magnitude vector. In particular, we theoretically show that the previously known properties of boundary detection translate to edge detection abilities in images. Furthermore, we demonstrate practical use cases of magnitude for machine learning applications and propose a novel magnitude model that consists of a computationally efficient magnitude computation and a learnable metric. By doing so, we address the computational hurdle that used to make magnitude impractical for many applications and open the way for the adoption of magnitude in machine learning research.
Driving styles summarize different driving behaviors that reflect in the movements of the vehicles. These behaviors may indicate a tendency to perform riskier maneuvers, consume more fuel or energy, break traffic rules, or drive carefully. Therefore, this paper presents a driving style recognition using Interval Type-2 Fuzzy Inference System with Multiple Experts Decision-Making for classifying drivers into calm, moderate and aggressive. This system receives as input features longitudinal and lateral kinematic parameters of the vehicle motion. The type-2 fuzzy sets are more robust than type-1 fuzzy sets when handling noisy data, because their membership function are also fuzzy sets. In addition, a multiple experts approach can reduce the bias and imprecision while building the fuzzy rulebase, which stores the knowledge of the fuzzy system. The proposed approach was evaluated using descriptive statistics analysis, and compared with clustering algorithms and a type-1 fuzzy inference system. The results show the tendency to associate lower kinematic profiles for the driving styles classified with the type-2 fuzzy inference system when compared to other algorithms, which is in line with the more conservative approach adopted in the aggregation of the experts' opinions.
Personalized diagnoses have not been possible due to sear amount of data pathologists have to bear during the day-to-day routine. This lead to the current generalized standards that are being continuously updated as new findings are reported. It is noticeable that these effective standards are developed based on a multi-source heterogeneous data, including whole-slide images and pathology and clinical reports. In this study, we propose a framework that combines pathological images and medical reports to generate a personalized diagnosis result for individual patient. We use nuclei-level image feature similarity and content-based deep learning method to search for a personalized group of population with similar pathological characteristics, extract structured prognostic information from descriptive pathology reports of the similar patient population, and assign importance of different prognostic factors to generate a personalized pathological diagnosis result. We use multi-source heterogeneous data from TCGA (The Cancer Genome Atlas) database. The result demonstrate that our framework matches the performance of pathologists in the diagnosis of renal cell carcinoma. This framework is designed to be generic, thus could be applied for other types of cancer. The weights could provide insights to the known prognostic factors and further guide more precise clinical treatment protocols.
Text-based person search (TBPS) aims at retrieving a target person from an image gallery with a descriptive text query. Solving such a fine-grained cross-modal retrieval task is challenging, which is further hampered by the lack of large-scale datasets. In this paper, we present a framework with two novel components to handle the problems brought by limited data. Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch. Secondly, we propose to transfer knowledge learned from existing coarse-grained large-scale datasets containing image-text pairs from drastically different problem domains to compensate for the lack of TBPS training data. A transfer learning method is designed so that useful information can be transferred despite the large domain gap. Armed with these components, our method achieves new state of the art on the CUHK-PEDES dataset with significant improvements over the prior art in terms of Rank-1 and mAP. Our code is available at https://github.com/BrandonHanx/TextReID.
Computational level explanations based on optimal feedback control with signal-dependent noise have been able to account for a vast array of phenomena in human sensorimotor behavior. However, commonly a cost function needs to be assumed for a task and the optimality of human behavior is evaluated by comparing observed and predicted trajectories. Here, we introduce inverse optimal control with signal-dependent noise, which allows inferring the cost function from observed behavior. To do so, we formalize the problem as a partially observable Markov decision process and distinguish between the agent's and the experimenter's inference problems. Specifically, we derive a probabilistic formulation of the evolution of states and belief states and an approximation to the propagation equation in the linear-quadratic Gaussian problem with signal-dependent noise. We extend the model to the case of partial observability of state variables from the point of view of the experimenter. We show the feasibility of the approach through validation on synthetic data and application to experimental data. Our approach enables recovering the costs and benefits implicit in human sequential sensorimotor behavior, thereby reconciling normative and descriptive approaches in a computational framework.
Table2Text systems generate textual output based on structured data utilizing machine learning. These systems are essential for fluent natural language interfaces in tools such as virtual assistants; however, left to generate freely these ML systems often produce misleading or unexpected outputs. GenNI (Generation Negotiation Interface) is an interactive visual system for high-level human-AI collaboration in producing descriptive text. The tool utilizes a deep learning model designed with explicit control states. These controls allow users to globally constrain model generations, without sacrificing the representation power of the deep learning models. The visual interface makes it possible for users to interact with AI systems following a Refine-Forecast paradigm to ensure that the generation system acts in a manner human users find suitable. We report multiple use cases on two experiments that improve over uncontrolled generation approaches, while at the same time providing fine-grained control. A demo and source code are available at https://genni.vizhub.ai .
State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors, but also gives a way to act and improve the classifier. We propose to discover those feature-value combinations (i.e., patterns) that strongly correlate with correct resp. erroneous predictions to obtain a global and interpretable description for arbitrary classifiers. We show this is an instance of the more general label description problem, which we formulate in terms of the Minimum Description Length principle. To discover a good pattern set, we develop the efficient Premise algorithm. Through an extensive set of experiments we show it performs very well in practice on both synthetic and real-world data. Unlike existing solutions, it ably recovers ground truth patterns, even on highly imbalanced data over many features. Through two case studies on Visual Question Answering and Named Entity Recognition, we confirm that Premise gives clear and actionable insight into the systematic errors made by modern NLP classifiers.
Human identification is one of the most common and critical tasks for condition monitoring, human-machine interaction, and providing assistive services in smart environments. Recently, human gait has gained new attention as a biometric for identification to achieve contactless identification from a distance robust to physical appearances. However, an important aspect of gait identification through wearables and image-based systems alike is accurate identification when limited information is available, for example, when only a fraction of the whole gait cycle or only a part of the subject body is visible. In this paper, we present a gait identification technique based on temporal and descriptive statistic parameters of different gait phases as the features and we investigate the performance of using only single gait phases for the identification task using a minimum number of sensors. It was shown that it is possible to achieve high accuracy of over 95.5 percent by monitoring a single phase of the whole gait cycle through only a single sensor. It was also shown that the proposed methodology could be used to achieve 100 percent identification accuracy when the whole gait cycle was monitored through pelvis and foot sensors combined. The ANN was found to be more robust to fewer data features compared to SVM and was concluded as the best machine algorithm for the purpose.
When designing Convolutional Neural Networks (CNNs), one must select the size\break of the convolutional kernels before training. Recent works show CNNs benefit from different kernel sizes at different layers, but exploring all possible combinations is unfeasible in practice. A more efficient approach is to learn the kernel size during training. However, existing works that learn the kernel size have a limited bandwidth. These approaches scale kernels by dilation, and thus the detail they can describe is limited. In this work, we propose FlexConv, a novel convolutional operation with which high bandwidth convolutional kernels of learnable kernel size can be learned at a fixed parameter cost. FlexNets model long-term dependencies without the use of pooling, achieve state-of-the-art performance on several sequential datasets, outperform recent works with learned kernel sizes, and are competitive with much deeper ResNets on image benchmark datasets. Additionally, FlexNets can be deployed at higher resolutions than those seen during training. To avoid aliasing, we propose a novel kernel parameterization with which the frequency of the kernels can be analytically controlled. Our novel kernel parameterization shows higher descriptive power and faster convergence speed than existing parameterizations. This leads to important improvements in classification accuracy.
As AI systems become increasingly powerful and pervasive, there are growing concerns about machines' morality or a lack thereof. Yet, teaching morality to machines is a formidable task, as morality remains among the most intensely debated questions in humanity, let alone for AI. Existing AI systems deployed to millions of users, however, are already making decisions loaded with moral implications, which poses a seemingly impossible challenge: teaching machines moral sense, while humanity continues to grapple with it. To explore this challenge, we introduce Delphi, an experimental framework based on deep neural networks trained directly to reason about descriptive ethical judgments, e.g., "helping a friend" is generally good, while "helping a friend spread fake news" is not. Empirical results shed novel insights on the promises and limits of machine ethics; Delphi demonstrates strong generalization capabilities in the face of novel ethical situations, while off-the-shelf neural network models exhibit markedly poor judgment including unjust biases, confirming the need for explicitly teaching machines moral sense. Yet, Delphi is not perfect, exhibiting susceptibility to pervasive biases and inconsistencies. Despite that, we demonstrate positive use cases of imperfect Delphi, including using it as a component model within other imperfect AI systems. Importantly, we interpret the operationalization of Delphi in light of prominent ethical theories, which leads us to important future research questions.
Inspection of tissues using a light microscope is the primary method of diagnosing many diseases, notably cancer. Highly multiplexed tissue imaging builds on this foundation, enabling the collection of up to 60 channels of molecular information plus cell and tissue morphology using antibody staining. This provides unique insight into disease biology and promises to help with the design of patient-specific therapies. However, a substantial gap remains with respect to visualizing the resulting multivariate image data and effectively supporting pathology workflows in digital environments on screen. We, therefore, developed Scope2Screen, a scalable software system for focus+context exploration and annotation of whole-slide, high-plex, tissue images. Our approach scales to analyzing 100GB images of 10^9 or more pixels per channel, containing millions of cells. A multidisciplinary team of visualization experts, microscopists, and pathologists identified key image exploration and annotation tasks involving finding, magnifying, quantifying, and organizing ROIs in an intuitive and cohesive manner. Building on a scope2screen metaphor, we present interactive lensing techniques that operate at single-cell and tissue levels. Lenses are equipped with task-specific functionality and descriptive statistics, making it possible to analyze image features, cell types, and spatial arrangements (neighborhoods) across image channels and scales. A fast sliding-window search guides users to regions similar to those under the lens; these regions can be analyzed and considered either separately or as part of a larger image collection. A novel snapshot method enables linked lens configurations and image statistics to be saved, restored, and shared. We validate our designs with domain experts and apply Scope2Screen in two case studies involving lung and colorectal cancers to discover cancer-relevant image features.
Income inequality is a distributional phenomenon. This paper examines the impact of U.S governor's party allegiance (Republican vs Democrat) on ethnic wage gap. A descriptive analysis of the distribution of yearly earnings of Whites and Blacks reveals a divergence in their respective shapes over time suggesting that aggregate analysis may mask important heterogeneous effects. This motivates a granular estimation of the comparative causal effect of governors' party affiliation on labor market outcomes. We use a regression discontinuity design (RDD) based on marginal electoral victories and samples of quantiles groups by wage and hours worked. Overall, the distributional causal estimations show that the vast majority of subgroups of black workers earnings are not affected by democrat governors' policies, suggesting the possible existence of structural factors in the labor markets that contribute to create and keep a wage trap and/or hour worked trap for most of the subgroups of black workers. Democrat governors increase the number of hours worked of black workers at the highest quartiles of earnings. A bivariate quantiles groups analysis shows that democrats decrease the total hours worked for black workers who have the largest number of hours worked and earn the least. Black workers earning more and working fewer hours than half of the sample see their number of hours worked increase under a democrat governor.