Search

The growth of recommender systems (RecSys) is driven by digitization and the need for personalized content in areas such as e-commerce and video streaming. The content in these systems often changes rapidly and therefore they constantly face the ongoing cold-start problem, where new items lack interaction data and are hard to value. Existing solutions for the cold-start problem, such as content-based recommenders and hybrid methods, leverage item metadata to determine item similarities. The main challenge with these methods is their reliance on structured and informative metadata to capture detailed item similarities, which may not always be available. This paper introduces a novel approach for cold-start item recommendation that utilizes the language model (LM) to estimate item similarities, which are further integrated as a Bayesian prior with classic recommender systems. This approach is generic and able to boost the performance of various recommenders. Specifically, our experiments integrate it with both sequential and collaborative filtering-based recommender and evaluate it on two real-world datasets, demonstrating the enhanced performance of the proposed approach., Comment: This paper is dedicated to cold-start item recommendation using language-model priors

While retrieval augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or irrelevant information. One common detection strategy involves prompting the LLM again to assess whether its response is grounded in the retrieved evidence, but this approach is costly. Alternatively, lightweight natural language inference (NLI) models for efficient grounding verification can be used at inference time. While existing pre-trained NLI models offer potential solutions, their performance remains subpar compared to larger models on realistic RAG inputs. RAG inputs are more complex than most datasets used for training NLI models and have characteristics specific to the underlying knowledge base, requiring adaptation of the NLI models to a specific target domain. Additionally, the lack of labeled instances in the target domain makes supervised domain adaptation, e.g., through fine-tuning, infeasible. To address these challenges, we introduce Automatic Generative Domain Adaptation (Auto-GDA). Our framework enables unsupervised domain adaptation through synthetic data generation. Unlike previous methods that rely on handcrafted filtering and augmentation strategies, Auto-GDA employs an iterative process to continuously improve the quality of generated samples using weak labels from less efficient teacher models and discrete optimization to select the most promising augmented samples. Experimental results demonstrate the effectiveness of our approach, with models fine-tuned on synthetic data using Auto-GDA often surpassing the performance of the teacher model and reaching the performance level of LLMs at 10 % of their computational cost.

Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private information about their training data. Here, we demonstrate a privacy vulnerability of diffusion models through a \emph{membership inference (MI) attack}, which aims to identify whether a target example belongs to the training set when given the trained diffusion model. Our proposed MI attack learns quantile regression models that predict (a quantile of) the distribution of reconstruction loss on examples not used in training. This allows us to define a granular hypothesis test for determining the membership of a point in the training set, based on thresholding the reconstruction loss of that point using a custom threshold tailored to the example. We also provide a simple bootstrap technique that takes a majority membership prediction over ``a bag of weak attackers'' which improves the accuracy over individual quantile regression models. We show that our attack outperforms the prior state-of-the-art attack while being substantially less computationally expensive -- prior attacks required training multiple ``shadow models'' with the same architecture as the model under attack, whereas our attack requires training only much smaller models.

Quantile Regression (QR) can be used to estimate aleatoric uncertainty in deep neural networks and can generate prediction intervals. Quantifying uncertainty is particularly important in critical applications such as clinical diagnosis, where a realistic assessment of uncertainty is essential in determining disease status and planning the appropriate treatment. The most common application of quantile regression models is in cases where the parametric likelihood cannot be specified. Although quantile regression is quite robust to outlier response observations, it can be sensitive to outlier covariate observations (features). Outlier features can compromise the performance of deep learning regression problems such as style translation, image reconstruction, and deep anomaly detection, potentially leading to misleading conclusions. To address this problem, we propose a robust solution for quantile regression that incorporates concepts from robust divergence. We compare the performance of our proposed method with (i) least trimmed quantile regression and (ii) robust regression based on the regularization of case-specific parameters in a simple real dataset in the presence of outlier. These methods have not been applied in a deep learning framework. We also demonstrate the applicability of the proposed method by applying it to a medical imaging translation task using diffusion models.

We revisit the problem of differentially private squared error linear regression. We observe that existing state-of-the-art methods are sensitive to the choice of hyperparameters -- including the ``clipping threshold'' that cannot be set optimally in a data-independent way. We give a new algorithm for private linear regression based on gradient boosting. We show that our method consistently improves over the previous state of the art when the clipping threshold is taken to be fixed without knowledge of the data, rather than optimized in a non-private way -- and that even when we optimize the hyperparameters of competitor algorithms non-privately, our algorithm is no worse and often better. In addition to a comprehensive set of experiments, we give theoretical insights to explain this behavior.

We provide a differentially private algorithm for producing synthetic data simultaneously useful for multiple tasks: marginal queries and multitask machine learning (ML). A key innovation in our algorithm is the ability to directly handle numerical features, in contrast to a number of related prior approaches which require numerical features to be first converted into {high cardinality} categorical features via {a binning strategy}. Higher binning granularity is required for better accuracy, but this negatively impacts scalability. Eliminating the need for binning allows us to produce synthetic data preserving large numbers of statistical queries such as marginals on numerical features, and class conditional linear threshold queries. Preserving the latter means that the fraction of points of each class label above a particular half-space is roughly the same in both the real and synthetic data. This is the property that is needed to train a linear classifier in a multitask setting. Our algorithm also allows us to produce high quality synthetic data for mixed marginal queries, that combine both categorical and numerical features. Our method consistently runs 2-5x faster than the best comparable techniques, and provides significant accuracy improvements in both marginal queries and linear prediction tasks for mixed-type datasets., Comment: The short version of this paper appears in the proceedings of NeurIPS-22

Despite impressive state-of-the-art performance on a wide variety of machine learning tasks, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we propose a novel approach that uses quantile regression for quantifying aleatoric uncertainty in both supervised and unsupervised lesion detection problems. The resulting confidence intervals can be used for lesion detection and segmentation. In the unsupervised setting, we combine quantile regression with the Variational AutoEncoder (VAE). Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection. The VAE models the output as a conditionally independent Gaussian characterized by its mean and variance. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. Here we describe an alternative Quantile-Regression VAE (QR-VAE) that avoids this variance shrinkage problem by directly estimating conditional quantiles for the input image. Using the estimated quantiles, we compute the conditional mean and variance for the input image from which we then detect outliers by thresholding at a false-discovery-rate corrected p-value. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. We show how BQR can be used to capture uncertainty in lesion boundaries in a manner that characterizes expert disagreement., Comment: Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://www.melba-journal.org/papers/2022:008.html. arXiv admin note: substantial text overlap with arXiv:2010.09042

We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals, subject to differential privacy. Our algorithm makes adaptive use of a continuous relaxation of the Projection Mechanism, which answers queries on the private dataset using simple perturbation, and then attempts to find the synthetic dataset that most closely matches the noisy answers. We use a continuous relaxation of the synthetic dataset domain which makes the projection loss differentiable, and allows us to use efficient ML optimization techniques and tooling. Rather than answering all queries up front, we make judicious use of our privacy budget by iteratively and adaptively finding queries for which our (relaxed) synthetic data has high error, and then repeating the projection. We perform extensive experimental evaluations across a range of parameters and datasets, and find that our method outperforms existing algorithms in many cases, especially when the privacy budget is small or the query class is large.

Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples (AEs) with small uniform norm-bounded perturbations across features to maintain the requirement of imperceptibility. However, uniform perturbations do not result in realistic AEs in domains such as malware, finance, and social networks. For these types of applications, features typically have some semantically meaningful dependencies. The key idea of our proposed approach is to enable non-uniform perturbations that can adequately represent these feature dependencies during adversarial training. We propose using characteristics of the empirical data distribution, both on correlations between the features and the importance of the features themselves. Using experimental datasets for malware classification, credit risk prediction, and spam detection, we show that our approach is more robust to real-world attacks. Finally, we present robustness certification utilizing non-uniform perturbation bounds, and show that non-uniform bounds achieve better certification., Comment: Accepted to NeurIPS 2021

Estimation of uncertainty in deep learning models is of vital importance, especially in medical imaging, where reliance on inference without taking into account uncertainty could lead to misdiagnosis. Recently, the probabilistic Variational AutoEncoder (VAE) has become a popular model for anomaly detection in applications such as lesion detection in medical images. The VAE is a generative graphical model that is used to learn the data distribution from samples and then generate new samples from this distribution. By training on normal samples, the VAE can be used to detect inputs that deviate from this learned distribution. The VAE models the output as a conditionally independent Gaussian characterized by means and variances for each output dimension. VAEs can therefore use reconstruction probability instead of reconstruction error for anomaly detection. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. We describe an alternative approach that avoids this variance shrinkage problem by using quantile regression. Using estimated quantiles to compute mean and variance under the Gaussian assumption, we compute reconstruction probability as a principled approach to outlier or anomaly detection. Results on simulated and Fashion MNIST data demonstrate the effectiveness of our approach. We also show how our approach can be used for principled heterogeneous thresholding for lesion detection in brain images.

We propose a robust variational autoencoder with $\beta$ divergence for tabular data (RTVAE) with mixed categorical and continuous features. Variational autoencoders (VAE) and their variations are popular frameworks for anomaly detection problems. The primary assumption is that we can learn representations for normal patterns via VAEs and any deviation from that can indicate anomalies. However, the training data itself can contain outliers. The source of outliers in training data include the data collection process itself (random noise) or a malicious attacker (data poisoning) who may target to degrade the performance of the machine learning model. In either case, these outliers can disproportionately affect the training process of VAEs and may lead to wrong conclusions about what the normal behavior is. In this work, we derive a novel form of a variational autoencoder for tabular data sets with categorical and continuous features that is robust to outliers in training data. Our results on the anomaly detection application for network traffic datasets demonstrate the effectiveness of our approach.

Dropout as a regularizer in deep neural networks has been less effective in convolutional layers than in fully connected layers. This is due to the fact that dropout drops features randomly. When features are spatially correlated as in the case of convolutional layers, information about the dropped pixels can still propagate to the next layers via neighboring pixels. In order to address this problem, more structured forms of dropout have been proposed. A drawback of these methods is that they do not adapt to the data. In this work, we introduce a novel structured regularization for convolutional layers, which we call DropCluster. Our regularizer relies on data-driven structure. It finds clusters of correlated features in convolutional layer outputs and drops the clusters randomly at each iteration. The clusters are learned and updated during model training so that they adapt both to the data and to the model weights. Our experiments on the ResNet-50 architecture demonstrate that our approach achieves better performance than DropBlock or other existing structured dropout variants. We also demonstrate the robustness of our approach when the size of training data is limited and when there is corruption in the data at test time., Comment: 11 pages, 10 figures, under review

We consider online forecasting problems for non-convex machine learning models. Forecasting introduces several challenges such as (i) frequent updates are necessary to deal with concept drift issues since the dynamics of the environment change over time, and (ii) the state of the art models are non-convex models. We address these challenges with a novel regret framework. Standard regret measures commonly do not consider both dynamic environment and non-convex models. We introduce a local regret for non-convex models in a dynamic environment. We present an update rule incurring a cost, according to our proposed local regret, which is sublinear in time T. Our update uses time-smoothed gradients. Using a real-world dataset we show that our time-smoothed approach yields several benefits when compared with state-of-the-art competitors: results are more stable against new data; training is more robust to hyperparameter selection; and our approach is more computationally efficient than the alternatives., Comment: NeurIPS2019. arXiv admin note: substantial text overlap with arXiv:1905.08850

The availability and easy access to digital communication increase the risk of copyrighted material piracy. In order to detect illegal use or distribution of data, digital watermarking has been proposed as a suitable tool. It protects the copyright of digital content by embedding imperceptible information into the data in the presence of an adversary. The goal of the adversary is to remove the copyrighted content of the data. Therefore, an efficient watermarking framework must be robust to multiple image-processing operations known as attacks that can alter embedded copyright information. Another line of research \textit{adversarial machine learning} also tackles with similar problems to guarantee robustness to imperceptible perturbations of the input. In this work, we propose to apply robust optimization from adversarial machine learning to improve the robustness of a CNN-based watermarking framework. Our experimental results on the COCO dataset show that the robustness of a watermarking framework can be improved by utilizing robust optimization in training., Comment: 5 pages, 1 figure, Machine Learning with Guarantees workshop at NeurIPS 2019

Machine learning methods often need a large amount of labeled training data. Since the training data is assumed to be the ground truth, outliers can severely degrade learned representations and performance of trained models. Here we apply concepts from robust statistics to derive a novel variational autoencoder that is robust to outliers in the training data. Variational autoencoders (VAEs) extract a lower-dimensional encoded feature representation from which we can generate new data samples. Robustness of autoencoders to outliers is critical for generating a reliable representation of particular data types in the encoded space when using corrupted training data. Our robust VAE is based on beta-divergence rather than the standard Kullback-Leibler (KL) divergence. Our proposed lower bound lead to a RVAE model that has the same computational complexity as the VAE and contains a single tuning parameter to control the degree of robustness. We demonstrate the performance of our $\beta$-divergence based autoencoder for a range of image datasets, showing improved robustness to outliers both qualitatively and quantitatively. We also illustrate the use of our robust VAE for outlier detection.

Here, we study different update rules in stochastic gradient descent (SGD) for online forecasting problems. The selection of the learning rate parameter is critical in SGD. However, it may not be feasible to tune this parameter in online learning. Therefore, it is necessary to have an update rule that is not sensitive to the selection of the learning parameter. Inspired by the local regret metric that we introduced previously, we propose to use time-smoothed gradients within SGD update. Using the public data set-- GEFCom2014, we validate that our approach yields more stable results than the other existing approaches. Furthermore, we show that such a simple approach is computationally efficient compared to the alternatives., Comment: ICML 2019, time series workshop

We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models even in offline settings. Hence, gradient based definition of regrets are common for both offline and online nonconvex problems. Recently, a notion of local gradient based regret was introduced. Inspired by the concept of calibration and a local gradient based regret, we introduce another definition of regret and we discuss why our definition is more interpretable for forecasting problems. We also provide bound analysis for our regret under certain assumptions., Comment: Continual Workshop at NIPS 2018, 2 figures, 9 pages

In many applications where collecting data is expensive, for example neuroscience or medical imaging, the sample size is typically small compared to the feature dimension. It is challenging in this setting to train expressive, non-linear models without overfitting. These datasets call for intelligent regularization that exploits known structure, such as correlations between the features arising from the measurement device. However, existing structured regularizers need specially crafted solvers, which are difficult to apply to complex models. We propose a new regularizer specifically designed to leverage structure in the data in a way that can be applied efficiently to complex models. Our approach relies on feature grouping, using a fast clustering algorithm inside a stochastic gradient descent loop: given a family of feature groupings that capture feature covariations, we randomly select these groups at each iteration. We show that this approach amounts to enforcing a denoising regularizer on the solution. The method is easy to implement in many model architectures, such as fully connected neural networks, and has a linear computational cost. We apply this regularizer to a real-world fMRI dataset and the Olivetti Faces datasets. Experiments on both datasets demonstrate that the proposed approach produces models that generalize better than those trained with conventional regularizers, and also improves convergence speed., Comment: 12 pages, 14 figures