Paper identifies food types from Yelp photos using machine learning.
problem Ineffective labeling of food photos on Yelp.
method Image pre-processing, CNN feature extraction, and classification algorithms.
result Identifies up to 10 food types from raw photos with high accuracy.
Deep learning predicts bridge load capacity from images.
problem Lack of data on aging bridges in post-disaster zones.
method Crowd-sourced images trained on a new CNN for multiclass classification.
result Improved prediction accuracy and practical optimisation.
Activates speech DNNs to generate understandable examples.
problem Difficulty in understanding DNN classifications for speech.
method Activation maximization to generate speech samples.
result Activation maximization can generate understandable speech samples.
Dataset of 50k hotels aids in human trafficking investigations.
problem Identify hotels from low-quality, occluded images.
method Curated dataset of 1M annotated hotel room images, baseline model with data augmentation.
result Demonstrated the feasibility of hotel recognition from challenging images.
Deep learning model detects and corrects outliers in crowd-sourced weather data.
problem Data quality issues in crowd-sourced weather data.
method Bayesian deep learning approach with Gaussian-uniform mixture density network.
result Automated outlier detection in spatio-temporal environmental modeling.
Bayesian model improves truth inference from highly redundant crowd annotations.
problem Inferring true annotations from highly redundant crowd annotations.
method Bayesian graphical model with conjugate priors and iterative expectation-maximisation inference.
result Our technique significantly outperforms majority vote heuristic at one-sided level 0.025.
Crowd-sourced mosquito audio dataset for malaria research.
problem Understanding mosquito locations for malaria reduction.
method Release of a large mosquito audio dataset with labels from contributors.
result Demonstrated the feasibility of training a CNN on mosquito audio data.
Study shows noisy data collection in ImageNet leads to biased model performance.
problem Noisy data collection in ImageNet datasets causes biased model performance.
method Human studies on ImageNet dataset to investigate design choices and their impact.
result Systematic misalignment between ImageNet benchmark and real-world task.
BUDS balances privacy and utility by shuffling data, achieving strong privacy with minimal loss.
problem Balancing privacy and utility in crowd-sourced statistical databases.
method One-hot encoding, iterative shuffling, loss estimation, risk minimization.
result Achieves ε=0.02 for privacy, maintaining a privacy bound of ε=ln[t/((n1−1)S)]. The paper tackles ranking experts based on their answers to questions, considering statistical and computational challenges.
problem Ranking experts based on their answers to questions, considering isotonic constraints.
method Investigates the existence of statistically optimal and computationally efficient procedures for ranking experts under isotonic constraints.
result Disproves the existence of computational-statistical gaps for the problem.
Regression problems assume every instance is annotated (labeled) with a real value, a form of annotation we call \emph{strong guidance}. In order for these annotations to be accurate, they must be the result of a precise experiment or measurement. However, in some cases additional \emph{weak guidance} might be given by…
Algorithm learns nearest neighbor graph from noisy distance queries.
problem Learning nearest neighbor graph from noisy distance samples.
method Active algorithm to find graph with high probability, analyzing query complexity.
result Empirically and theoretically efficient, needing only O(n log(n)Delta^-2) queries.
New algorithms find all ε-good arms in stochastic bandits.
problem Finding all arms with means above a specified threshold in stochastic bandits.
method Two algorithms introduced to identify all ε-good arms.
result Demonstrated great empirical performance on large datasets.
This paper considers extractive summarisation in a comparative setting: given two or more document groups (e.g., separated by publication time), the goal is to select a small number of documents that are representative of each group, and also maximally distinguishable from other groups. We formulate a set of new object…
Wide-AdGraph detects ads and trackers using a graph of resource requests.
problem Detecting and blocking ad trackers to protect user privacy.
method Combining a large-scale graph of resource requests from multiple websites to train a machine learning algorithm.
result High accuracy (96.1% biased, 90.9% unbiased) in detecting ads and trackers.
Python models predict stock sentiment for market-beating returns.
problem Predicting public sentiment for stock trading.
method Crowd-sourced labeled data, trained and evaluated various models.
result Best models predict market-beating returns from public sentiment.
Community moderation drifts towards majority, study finds.
problem How to ensure crowd-sourced moderation systems trust and reward accurate evaluations.
method Consensus-based auditing with a two-stage algorithm that weights contributors by the stability of their past residuals.
result Minority contributors' evaluations drift towards the majority, and their participation share falls on controversial topics.
Crowdsourced predictions from microservices improve supply chain efficiency.
problem Improving supply chain efficiency through high-quality predictions.
method Trials of a multi-agent system with microservices and economic incentives.
result Empirical lessons suggest potential for a Prediction Web.
We evaluated the effectiveness of an automated bird sound identification system in a situation that emulates a realistic, typical application. We trained classification algorithms on a crowd-sourced collection of bird audio recording data and restricted our training methods to be completely free of manual intervention.…
In this paper we address a classification problem where two sources of labels with different levels of fidelity are available. Our approach is to combine data from both sources by applying a co-kriging schema on latent functions, which allows the model to account item-dependent labeling discrepancy. We provide an exten…
The paper tackles identifying multiple best arms in stochastic bandits, improving sample efficiency.
problem Identifying multiple best arms in stochastic multi-armed bandits.
method Developed a fully sequential PAC algorithm, GLUCB, and presented lower and upper bounds.
result Improved sample efficiency for identifying multiple best arms.
Study analyzes online abuse against women journalists and politicians on Twitter.
problem Online abuse against women journalists and politicians on Twitter.
method Crowdsourced analysis of a curated dataset of labeled tweets, accounting for variability in abuse perception.
result Technical backbone for raising awareness and improving social media standards.
We define the intrinsic scale at which a network begins to reveal its identity as the scale at which subgraphs in the network (created by a random walk) are distinguishable from similar sized subgraphs in a perturbed copy of the network. We conduct an extensive study of intrinsic scale for several networks, ranging fro…
Paper introduces metrics to detect unintended bias in text classifiers.
problem Unintended bias in machine learning classifiers.
method Threshold-agnostic metrics considering various score distribution variations across groups.
result New metrics reveal subtle unintended bias in public models.
LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
problem Behavioral biases in LLMs' stock return forecasts.
method Comparison of LLM forecasts with crowd-sourced estimates and historical data.
result LLMs overestimate stock returns and are less accurate at predicting extreme outcomes.
Efficiently augments triplet data for better data analytics.
problem Lack of direct pairwise distance information for data analysis.
method Triplets augmentation to infer hidden information from existing data.
result Improves quality of kernel-based and kernel-free data analytics.
This paper describes and evaluates the use of Generative Adversarial Networks (GANs) for path planning in support of smart mobility applications such as indoor and outdoor navigation applications, individualized wayfinding for people with disabilities (e.g., vision impairments, physical disabilities, etc.), path planni…
The paper investigates how data imbalance affects fairness and accuracy in differentially private deep learning.
problem Impact of data imbalance on fairness and accuracy in differentially private deep learning.
method Study the effects of different levels of imbalance in the data on the accuracy and fairness of decisions made by a model trained with differential privacy.
result Small imbalances and loose privacy guarantees can cause disparate impacts on model accuracy and fairness.
Noisy labeled data is more a norm than a rarity for crowd sourced contents. It is effective to distill noise and infer correct labels through aggregation results from crowd workers. To ensure the time relevance and overcome slow responses of workers, online label aggregation is increasingly requested, calling for solut…
World wide road traffic fatality and accident rates are high, and this is true even in technologically advanced countries like the USA. Despite the advances in Intelligent Transportation Systems, safe transportation routing i.e., finding safest routes is largely an overlooked paradigm. In recent years, large amount of …
Paper tackles super-resolving labels for weakly labeled data.
problem Real-world data scarcity with expertly labeled data.
method Nested loop with KDE to super-resolve labels.
result KDE super-resolves labels more accurately than baselines.
Foot-mounted inertial positioning (FMIP) can face problems of inertial drifts and unknown initial states in real applications, which renders the estimated trajectories inaccurate and not obtained in a well defined coordinate system for matching trajectories of different users. In this paper, an approach adopting receiv…
When the residents of Flint learned that lead had contaminated their water system, the local government made water-testing kits available to them free of charge. The city government published the results of these tests, creating a valuable dataset that is key to understanding the causes and extent of the lead contamina…
Hölder-DPO aligns models robustly with noisy human feedback.
problem No existing alignment methods can handle severe label noise.
method Proposes Hölder-DPO, a principled alignment loss with provable redescending property.
result Hölder-DPO enables scalable human feedback valuation and improves model alignment.
Gradient descent solves sparse skill estimation in crowdsourcing.
problem Crowd-sourced worker skill estimation with sparse and irregular assignments.
method Rank-one matrix completion and projected gradient descent.
result Skill estimates converge to global optima for specific sampling matrices.
This paper evaluates a method to improve representations using incomplete external evidence across tasks.
problem Increasing labelled data quality and quantity is challenging due to manual labelling errors and noise.
method Evidence Transfer method using incomplete categorical external evidence.
result Evidence Transfer proves effective and robust against different levels of incompleteness.
Model predicts political ideology using context vectors to mitigate bias and scarcity.
problem Scarcity and selection bias in political ideology prediction.
method Proposes a statistical model decomposing embeddings into context and position vectors, training an end-to-end model for deployment.
result Model can predict ideological labels even with minimal biased data, outperforming state-of-the-art methods.
Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth…
A new method uses RBMs to handle incomplete multi-output data.
problem Handling incomplete multi-output data with dependencies between features and labels.
method Adapted RBM algorithm based on mean-field equations for joint imputation and classification.
result Efficiently solves problems with missing features and labels.
Paper tackles noisy S-D data for classification.
problem Learning from noisy Similar (S) and Dissimilar (D) pairs.
method Proposes two algorithms to learn from noisy S-D data under two noise models.
result Noise-informed algorithms outperform noise-blind baselines.
Most work in machine reading focuses on question answering problems where the answer is directly expressed in the text to read. However, many real-world question answering problems require the reading of text not because it contains the literal answer, but because it contains a recipe to derive an answer together with …
Enhances dialogue model with persona attributes using adversarial learning.
problem Improving dialogue models to better capture speaker identity and topic.
method Adversarial learning framework with a dual discriminator system.
result phredGAN outperforms persona Seq2Seq model in various datasets.
Wisdom of the crowd, the collective intelligence derived from responses of multiple human or machine individuals to the same questions, can be more accurate than each individual, and improve social decision-making and prediction accuracy. This can also integrate multiple programs or datasets, each as an individual, for…
We study the problem of learning a distribution from samples, when the underlying distribution is a mixture of product distributions over discrete domains. This problem is motivated by several practical applications such as crowd-sourcing, recommendation systems, and learning Boolean functions. The existing solutions e…
Trans-Sense uses smartphones to predict public transit wait times and schedules.
problem Traffic congestion and lack of public transportation in developing countries.
method Crowdsourced mobile phones to estimate waiting times and transit schedules.
result Achieves high accuracy in predicting passenger arrival times and station dimensions.
Study evaluates fairness of machine learning models on Kaggle and finds some optimization techniques can induce unfairness.
problem Ensuring fairness of machine learning models used in important decisions.
method Empirical evaluation of 40 top-rated models from Kaggle on 5 tasks, applying 7 mitigation techniques.
result Some model optimization techniques induce unfairness; mitigation in pre-processing is preferred.
New bounds on majority voting's accuracy for multi-class classification problems.
problem Determining the accuracy of majority voting for multi-class classification.
method Analyzing the majority voting function under different voter conditions and distributions.
result The error rate of majority voting exponentially decays or grows with the number of voters under certain conditions.
CatSIM measures image similarity robustly to small changes.
problem Measuring similarity between images, especially with small perturbations.
method Uses structural similarity image quality paradigm, robust to small location changes.
result Structural similarity between images rated higher when not entirely overlapping.