Modern city governance relies heavily on crowdsourcing (or "co-production") to identify problems such as downed trees and power-lines. A major concern in these systems is that residents do not report problems at the same rates, leading to an inequitable allocation of government resources. However, measuring such under-reporting is a difficult statistical task, as, almost by definition, we do not observe incidents that are not reported. Thus, distinguishing between low reporting rates and low ground-truth incident rates is challenging. We develop a method to identify (heterogeneous) reporting rates, without using external (proxy) ground truth data. Our insight is that rates on $\textit{duplicate}$ reports about the same incident can be leveraged, to turn the question into a standard Poisson rate estimation task -- even though the full incident reporting interval is also unobserved. We apply our method to over 100,000 resident reports made to the New York City Department of Parks and Recreation, finding that there are substantial spatial and socio-economic disparities in reporting rates, even after controlling for incident characteristics.
相關內容
Accurate and interpretable prediction of survey response rates is important from an operational standpoint. The US Census Bureau's well-known ROAM application uses principled statistical models trained on the US Census Planning Database data to identify hard-to-survey areas. An earlier crowdsourcing competition revealed that an ensemble of regression trees led to the best performance in predicting survey response rates; however, the corresponding models could not be adopted for the intended application due to limited interpretability. In this paper, we present new interpretable statistical methods to predict, with high accuracy, response rates in surveys. We study sparse nonparametric additive models with pairwise interactions via $\ell_0$-regularization, as well as hierarchically structured variants that provide enhanced interpretability. Despite strong methodological underpinnings, such models can be computationally challenging -- we present new scalable algorithms for learning these models. We also establish novel non-asymptotic error bounds for the proposed estimators. Experiments based on the US Census Planning Database demonstrate that our methods lead to high-quality predictive models that permit actionable interpretability for different segments of the population. Interestingly, our methods provide significant gains in interpretability without losing in predictive performance to state-of-the-art black-box machine learning methods based on gradient boosting and feedforward neural networks. Our code implementation in python is available at //github.com/ShibalIbrahim/Additive-Models-with-Structured-Interactions.
Over the past decade, machine learning revolutionized vision-based quality assessment for which convolutional neural networks (CNNs) have now become the standard. In this paper, we consider a potential next step in this development and describe a quanvolutional neural network (QNN) algorithm that efficiently maps classical image data to quantum states and allows for reliable image analysis. We practically demonstrate how to leverage quantum devices in computer vision and how to introduce quantum convolutions into classical CNNs. Dealing with a real world use case in industrial quality control, we implement our hybrid QNN model within the PennyLane framework and empirically observe it to achieve better predictions using much fewer training data than classical CNNs. In other words, we empirically observe a genuine quantum advantage for an industrial application where the advantage is due to superior data encoding.
Recent studies have demonstrated that gradient matching-based dataset synthesis, or dataset condensation (DC), methods can achieve state-of-the-art performance when applied to data-efficient learning tasks. However, in this study, we prove that the existing DC methods can perform worse than the random selection method when task-irrelevant information forms a significant part of the training dataset. We attribute this to the lack of participation of the contrastive signals between the classes resulting from the class-wise gradient matching strategy. To address this problem, we propose Dataset Condensation with Contrastive signals (DCC) by modifying the loss function to enable the DC methods to effectively capture the differences between classes. In addition, we analyze the new loss function in terms of training dynamics by tracking the kernel velocity. Furthermore, we introduce a bi-level warm-up strategy to stabilize the optimization. Our experimental results indicate that while the existing methods are ineffective for fine-grained image classification tasks, the proposed method can successfully generate informative synthetic datasets for the same tasks. Moreover, we demonstrate that the proposed method outperforms the baselines even on benchmark datasets such as SVHN, CIFAR-10, and CIFAR-100. Finally, we demonstrate the high applicability of the proposed method by applying it to continual learning tasks.
The U.S. COVID-19 Forecast Hub aggregates forecasts of the short-term burden of COVID-19 in the United States from many contributing teams. We study methods for building an ensemble that combines forecasts from these teams. These experiments have informed the ensemble methods used by the Hub. To be most useful to policy makers, ensemble forecasts must have stable performance in the presence of two key characteristics of the component forecasts: (1) occasional misalignment with the reported data, and (2) instability in the relative performance of component forecasters over time. Our results indicate that in the presence of these challenges, an untrained and robust approach to ensembling using an equally weighted median of all component forecasts is a good choice to support public health decision makers. In settings where some contributing forecasters have a stable record of good performance, trained ensembles that give those forecasters higher weight can also be helpful.
Content moderation research typically prioritizes representing and addressing challenges for one group of stakeholders or communities in one type of context. While taking a focused approach is reasonable or even favorable for empirical case studies, it does not address how content moderation works in multiple contexts. Through a systematic literature review of 86 content moderation papers that document empirical studies, we seek to uncover patterns and tensions within past content moderation research. We find that content moderation can be characterized as a series of trade-offs around moderation actions, styles, philosophies, and values. We discuss how facilitating cooperation and preventing abuse, two key elements in Grimmelmann's definition of moderation, are inherently dialectical in practice. We close by showing how researchers, designers, and moderators can use our framework of trade-offs in their own work, and arguing that trade-offs should be of central importance in investigating and designing content moderation.
Bitcoin is a digital currency designed to rely on a decentralized, trustless network of anonymous agents. Using a pseudonymous-address-linking procedure that achieves >99% sensitivity and >99% specificity, we reveal that between launch (January 3rd, 2009), and when the price reached $1 (February 9th, 2011), most bitcoin was mined by only sixty-four agents. This was due to the rapid emergence of Pareto distributions in bitcoin income, producing such extensive resource centralization that almost all contemporary bitcoin addresses can be connected to these top agents by a chain of six transactions. Centralization created a social dilemma. Attackers could routinely exploit bitcoin via a "51% attack", making it possible for them to repeatedly spend the same bitcoins. Yet doing so would harm the community. Strikingly, we find that potential attackers always chose to cooperate instead. We model this dilemma using an N-player Centipede game in which anonymous players can choose to exploit, and thereby undermine, an appreciating good. Combining theory and economic experiments, we show that, even when individual payoffs are unchanged, cooperation is more frequent when the game is played by an anonymous group. Although bitcoin was designed to rely on a decentralized, trustless network of anonymous agents, its early success rested instead on cooperation among a small group of altruistic founders.
Plagiarism in introductory programming courses is an enormous challenge for both students and institutions. For students, relying on the work of others too early in their academic development can make it impossible to acquire necessary skills for independent success in the future. For institutions, widespread student cheating can dilute the quality of the educational experience being offered. Currently available solutions consider only pairwise comparisons between student submissions and focus on punitive deterrence. Our approach instead relies on a class-wide statistical characterization that can be clearly and securely shared with students via an intuitive new p-value representing independence of student effort. A pairwise, compression-based similarity detection algorithm captures relationships between assignments more accurately. An automated deterrence system is used to warn students that their behavior is being closely monitored. High-confidence instances are made directly available for instructor review using our open-source toolkit. An unbiased scoring system aids students and the instructor in understanding true independence of effort. Preliminary results indicate that the system can provide meaningful measurements of independence from week one, improving the efficacy of technical education.
The accurate and interpretable prediction of future events in time-series data often requires the capturing of representative patterns (or referred to as states) underpinning the observed data. To this end, most existing studies focus on the representation and recognition of states, but ignore the changing transitional relations among them. In this paper, we present evolutionary state graph, a dynamic graph structure designed to systematically represent the evolving relations (edges) among states (nodes) along time. We conduct analysis on the dynamic graphs constructed from the time-series data and show that changes on the graph structures (e.g., edges connecting certain state nodes) can inform the occurrences of events (i.e., time-series fluctuation). Inspired by this, we propose a novel graph neural network model, Evolutionary State Graph Network (EvoNet), to encode the evolutionary state graph for accurate and interpretable time-series event prediction. Specifically, Evolutionary State Graph Network models both the node-level (state-to-state) and graph-level (segment-to-segment) propagation, and captures the node-graph (state-to-segment) interactions over time. Experimental results based on five real-world datasets show that our approach not only achieves clear improvements compared with 11 baselines, but also provides more insights towards explaining the results of event predictions.
Multi-relation Question Answering is a challenging task, due to the requirement of elaborated analysis on questions and reasoning over multiple fact triples in knowledge base. In this paper, we present a novel model called Interpretable Reasoning Network that employs an interpretable, hop-by-hop reasoning process for question answering. The model dynamically decides which part of an input question should be analyzed at each hop; predicts a relation that corresponds to the current parsed results; utilizes the predicted relation to update the question representation and the state of the reasoning process; and then drives the next-hop reasoning. Experiments show that our model yields state-of-the-art results on two datasets. More interestingly, the model can offer traceable and observable intermediate predictions for reasoning analysis and failure diagnosis, thereby allowing manual manipulation in predicting the final answer.
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a cause. To circumvent this problem, we propose a neural network component that allows robust counting from object proposals. Experiments on a toy task show the effectiveness of this component and we obtain state-of-the-art accuracy on the number category of the VQA v2 dataset without negatively affecting other categories, even outperforming ensemble models with our single model. On a difficult balanced pair metric, the component gives a substantial improvement in counting over a strong baseline by 6.6%.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191