arXiv subjects

Theodoros Rekatsinas

Publications and source records attributed to Theodoros Rekatsinas.

34 records · Page 2Linked to original sources

arXiv2020

Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models

Directed graphical models (DGMs) are a class of probabilistic models that are widely used for predictive analysis in sensitive domains, such as medical diagnostics. In this paper we present an algorithm for differentially private learning of the parameters of a DGM with a publicly known graph structure over fully observed data. Our solution optimizes for the utility of inference queries over the DGM and \textit{adds noise that is customized to the properties of the private input dataset and the graph structure of the DGM}. To the best of our knowledge, this is the first explicit data-dependent privacy budget allocation algorithm for DGMs. We compare our algorithm with a standard data-independent approach over a diverse suite of DGM benchmarks and demonstrate that our solution requires a privacy budget that is $3\times$ smaller to obtain the same or higher utility.

cs.LG↗

arXiv2020

Principal Component Networks: Parameter Reduction Early in Training

Recent works show that overparameterized networks contain small subnetworks that exhibit comparable accuracy to the full model when trained in isolation. These results highlight the potential to reduce training costs of deep neural networks without sacrificing generalization performance. However, existing approaches for finding these small networks rely on expensive multi-round train-and-prune procedures and are non-practical for large data sets and models. In this paper, we show how to find small networks that exhibit the same performance as their overparameterized counterparts after only a few training epochs. We find that hidden layer activations in overparameterized networks exist primarily in subspaces smaller than the actual model width. Building on this observation, we use PCA to find a basis of high variance for layer inputs and represent layer weights using these directions. We eliminate all weights not relevant to the found PCA basis and term these network architectures Principal Component Networks. On CIFAR-10 and ImageNet, we show that PCNs train faster and use less energy than overparameterized models, without accuracy loss. We find that our transformation leads to networks with up to 23.8x fewer parameters, with equal or higher end-model accuracy---in some cases we observe improvements up to 3%. We also show that ResNet-20 PCNs outperform deep ResNet-110 networks while training faster.

cs.LG↗

arXiv2020

Record fusion: A learning approach

Record fusion is the task of aggregating multiple records that correspond to the same real-world entity in a database. We can view record fusion as a machine learning problem where the goal is to predict the "correct" value for each attribute for each entity. Given a database, we use a combination of attribute-level, recordlevel, and database-level signals to construct a feature vector for each cell (or (row, col)) of that database. We use this feature vector alongwith the ground-truth information to learn a classifier for each of the attributes of the database. Our learning algorithm uses a novel stagewise additive model. At each stage, we construct a new feature vector by combining a part of the original feature vector with features computed by the predictions from the previous stage. We then learn a softmax classifier over the new feature space. This greedy stagewise approach can be viewed as a deep model where at each stage, we are adding more complicated non-linear transformations of the original feature vector. We show that our approach fuses records with an average precision of ~98% when source information of records is available, and ~94% without source information across a diverse array of real-world datasets. We compare our approach to a comprehensive collection of data fusion and entity consolidation methods considered in the literature. We show that our approach can achieve an average precision improvement of ~20%/~45% with/without source information respectively.

cs.LG↗

arXiv2020

An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation

Generalization Performance of Deep Learning models trained using Empirical Risk Minimization can be improved significantly by using Data Augmentation strategies such as simple transformations, or using Mixed Samples. We attempt to empirically analyze the impact of such strategies on the transfer of generalization between teacher and student models in a distillation setup. We observe that if a teacher is trained using any of the mixed sample augmentation strategies, such as MixUp or CutMix, the student model distilled from it is impaired in its generalization capabilities. We hypothesize that such strategies limit a model's capability to learn example-specific features, leading to a loss in quality of the supervision signal during distillation. We present a novel Class-Discrimination metric to quantitatively measure this dichotomy in performance and link it to the discriminative capacity induced by the different strategies on a network's latent space.

cs.CV↗

arXiv2019

MLSys: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains a significant obstacle, in large part due to the radically different development and deployment profile of modern ML methods, and the range of practical concerns that come with broader adoption. We propose to foster a new systems machine learning research community at the intersection of the traditional systems and ML communities, focused on topics such as hardware systems for ML, software systems for ML, and ML optimized for metrics beyond predictive accuracy. To do this, we describe a new conference, MLSys, that explicitly targets research at the intersection of systems and machine learning with a program committee split evenly between experts in systems and ML, and an explicit focus on topics at the intersection of the two.

cs.LG↗

arXiv2019

Fine-Grained Object Detection over Scientific Document Images with Region Embeddings

We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coarse elements such as tables and figures to fine elements such as equations and section headers. We find that current object detectors fail to produce properly localized region proposals over such page objects. We revisit the original R-CNN model and present a method for generating fine-grained proposals over document elements. We also present a region embedding model that uses the convolutional maps of a proposal's neighbors as context to produce an embedding for each proposal. This region embedding is able to capture the semantic relationships between a target region and its surrounding context. Our end-to-end model produces an embedding for each proposal, then classifies each proposal by using a multi-head attention model that attends to the most important neighbors of a proposal. To evaluate our model, we collect and annotate a dataset of publications from heterogeneous journals. We show that our model, referred to as Attentive-RCNN, yields a 17% mAP improvement compared to standard object detection models.

cs.CV↗

arXiv2019

Approximate Inference in Structured Instances with Noisy Categorical Observations

We study the problem of recovering the latent ground truth labeling of a structured instance with categorical random variables in the presence of noisy observations. We present a new approximate algorithm for graphs with categorical variables that achieves low Hamming error in the presence of noisy vertex and edge observations. Our main result shows a logarithmic dependency of the Hamming error to the number of categories of the random variables. Our approach draws connections to correlation clustering with a fixed number of clusters. Our results generalize the works of Globerson et al. (2015) and Foster et al. (2018), who study the hardness of structured prediction under binary labels, to the case of categorical labels.

cs.LG↗

arXiv2019

Learning Functional Dependencies with Sparse Regression

We study the problem of discovering functional dependencies (FD) from a noisy dataset. We focus on FDs that correspond to statistical dependencies in a dataset and draw connections between FD discovery and structure learning in probabilistic graphical models. We show that discovering FDs from a noisy dataset is equivalent to learning the structure of a graphical model over binary random variables, where each random variable corresponds to a functional of the dataset attributes. We build upon this observation to introduce AutoFD a conceptually simple framework in which learning functional dependencies corresponds to solving a sparse regression problem. We show that our methods can recover true functional dependencies across a diverse array of real-world and synthetic datasets, even in the presence of noisy or missing data. We find that AutoFD scales to large data instances with millions of tuples and hundreds of attributes while it yields an average F1 improvement of 2 times against state-of-the-art FD discovery methods.

cs.DB↗

arXiv2019

HoloDetect: Few-Shot Learning for Error Detection

We introduce a few-shot learning framework for error detection. We show that data augmentation (a form of weak supervision) is key to training high-quality, ML-based error detection models that require minimal human involvement. Our framework consists of two parts: (1) an expressive model to learn rich representations that capture the inherent syntactic and semantic heterogeneity of errors; and (2) a data augmentation model that, given a small seed of clean records, uses dataset-specific transformations to automatically generate additional training data. Our key insight is to learn data augmentation policies from the noisy input dataset in a weakly supervised manner. We show that our framework detects errors with an average precision of ~94% and an average recall of ~93% across a diverse array of datasets that exhibit different types and amounts of errors. We compare our approach to a comprehensive collection of error detection methods, ranging from traditional rule-based methods to ensemble-based and active learning approaches. We show that data augmentation yields an average improvement of 20 F1 points while it requires access to 3x fewer labeled examples compared to other ML approaches.

cs.DB↗

arXiv2019

A Formal Framework For Probabilistic Unclean Databases

Most theoretical frameworks that focus on data errors and inconsistencies follow logic-based reasoning. Yet, practical data cleaning tools need to incorporate statistical reasoning to be effective in real-world data cleaning tasks. Motivated by these empirical successes, we propose a formal framework for unclean databases, where two types of statistical knowledge are incorporated: The first represents a belief of how intended (clean) data is generated, and the second represents a belief of how noise is introduced in the actual observed database instance. To capture this noisy channel model, we introduce the concept of a Probabilistic Unclean Database (PUD), a triple that consists of a probabilistic database that we call the intention, a probabilistic data transformator that we call the realization and captures how noise is introduced, and a dirty observed database instance that we call the observation. We define three computational problems in the PUD framework: cleaning (infer the most probable clean instance given a PUD), probabilistic query answering (compute the probability of an answer tuple over the unclean observed instance), and learning (estimate the most likely intention and realization models of a PUD given a collection of training data). We illustrate the PUD framework on concrete representations of the intention and realization, show that they generalize traditional concepts of repairs such as cardinality and value repairs, draw connection to consistent query answering, and prove tractability results. We further show that parameters can be learned in practical instantiations, and in fact, prove that under certain conditions we can learn a PUD directly from a single dirty database instance without any need for clean examples.

cs.DB↗

arXiv2018

Fonduer: Knowledge Base Construction from Richly Formatted Data

We focus on knowledge base construction (KBC) from richly formatted data. In contrast to KBC from text or tabular data, KBC from richly formatted data aims to extract relations conveyed jointly via textual, structural, tabular, and visual expressions. We introduce Fonduer, a machine-learning-based KBC system for richly formatted data. Fonduer presents a new data model that accounts for three challenging characteristics of richly formatted data: (1) prevalent document-level relations, (2) multimodality, and (3) data variety. Fonduer uses a new deep-learning model to automatically capture the representation (i.e., features) needed to learn how to extract relations from richly formatted data. Finally, Fonduer provides a new programming model that enables users to convert domain expertise, based on multiple modalities of information, to meaningful signals of supervision for training a KBC system. Fonduer-based KBC systems are in production for a range of use cases, including at a major online retailer. We compare Fonduer against state-of-the-art KBC approaches in four different domains. We show that Fonduer achieves an average improvement of 41 F1 points on the quality of the output knowledge base---and in some cases produces up to 1.87x the number of correct entries---compared to expert-curated public knowledge bases. We also conduct a user study to assess the usability of Fonduer's new programming model. We show that after using Fonduer for only 30 minutes, non-domain experts are able to design KBC systems that achieve on average 23 F1 points higher quality than traditional machine-learning-based KBC approaches.

cs.DB↗

arXiv2017

HoloClean: Holistic Data Repairs with Probabilistic Inference

We introduce HoloClean, a framework for holistic data repairing driven by probabilistic inference. HoloClean unifies existing qualitative data repairing approaches, which rely on integrity constraints or external data sources, with quantitative data repairing methods, which leverage statistical properties of the input data. Given an inconsistent dataset as input, HoloClean automatically generates a probabilistic program that performs data repairing. Inspired by recent theoretical advances in probabilistic inference, we introduce a series of optimizations which ensure that inference over HoloClean's probabilistic model scales to instances with millions of tuples. We show that HoloClean scales to instances with millions of tuples and find data repairs with an average precision of ~90% and an average recall of above ~76% across a diverse array of datasets exhibiting different types of errors. This yields an average F1 improvement of more than 2x against state-of-the-art methods.

cs.DB↗

arXiv2016

SLiMFast: Guaranteed Results for Data Fusion and Source Reliability

We focus on data fusion, i.e., the problem of unifying conflicting data from data sources into a single representation by estimating the source accuracies. We propose SLiMFast, a framework that expresses data fusion as a statistical learning problem over discriminative probabilistic models, which in many cases correspond to logistic regression. In contrast to previous approaches that use complex generative models, discriminative models make fewer distributional assumptions over data sources and allow us to obtain rigorous theoretical guarantees. Furthermore, we show how SLiMFast enables incorporating domain knowledge into data fusion, yielding accuracy improvements of up to 50\% over state-of-the-art baselines. Building upon our theoretical results, we design an optimizer that obviates the need for users to manually select an algorithm for learning SLiMFast's parameters. We validate our optimizer on multiple real-world datasets and show that it can accurately predict the learning algorithm that yields the best data fusion results.

cs.DB↗

arXiv2015

CrowdGather: Entity Extraction over Structured Domains

Crowdsourced entity extraction is often used to acquire data for many applications, including recommendation systems, construction of aggregated listings and directories, and knowledge base construction. Current solutions focus on entity extraction using a single query, e.g., only using "give me another restaurant", when assembling a list of all restaurants. Due to the cost of human labor, solutions that focus on a single query can be highly impractical. In this paper, we leverage the fact that entity extraction often focuses on {\em structured domains}, i.e., domains that are described by a collection of attributes, each potentially exhibiting hierarchical structure. Given such a domain, we enable a richer space of queries, e.g., "give me another Moroccan restaurant in Manhattan that does takeout". Naturally, enabling a richer space of queries comes with a host of issues, especially since many queries return empty answers. We develop new statistical tools that enable us to reason about the gain of issuing {\em additional queries} given little to no information, and show how we can exploit the overlaps across the results of queries for different points of the data domain to obtain accurate estimates of the gain. We cast the problem of {\em budgeted entity extraction} over large domains as an adaptive optimization problem that seeks to maximize the number of extracted entities, while minimizing the overall extraction costs. We evaluate our techniques with experiments on both synthetic and real-world datasets, demonstrating a yield of up to 4X over competing approaches for the same budget.

cs.DB↗

arXiv2013

Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss

We propose a modular framework for multi-relational learning via tensor decomposition. In our learning setting, the training data contains multiple types of relationships among a set of objects, which we represent by a sparse three-mode tensor. The goal is to predict the values of the missing entries. To do so, we model each relationship as a function of a linear combination of latent factors. We learn this latent representation by computing a low-rank tensor decomposition, using quasi-Newton optimization of a weighted objective function. Sparsity in the observed data is captured by the weighted objective, leading to improved accuracy when training data is limited. Exploiting sparsity also improves efficiency, potentially up to an order of magnitude over unweighted approaches. In addition, our framework accommodates arbitrary combinations of smooth, task-specific loss functions, making it better suited for learning different types of relations. For the typical cases of real-valued functions and binary relations, we propose several loss functions and derive the associated parameter gradients. We evaluate our method on synthetic and real data, showing significant improvements in both accuracy and scalability over related factorization techniques.

cs.LG↗

arXiv2013

On Sharing Private Data with Multiple Non-Colluding Adversaries

We present SPARSI, a theoretical framework for partitioning sensitive data across multiple non-colluding adversaries. Most work in privacy-aware data sharing has considered disclosing summaries where the aggregate information about the data is preserved, but sensitive user information is protected. Nonetheless, there are applications, including online advertising, cloud computing and crowdsourcing markets, where detailed and fine-grained user-data must be disclosed. We consider a new data sharing paradigm and introduce the problem of privacy-aware data partitioning, where a sensitive dataset must be partitioned among k untrusted parties (adversaries). The goal is to maximize the utility derived by partitioning and distributing the dataset, while minimizing the amount of sensitive information disclosed. The data should be distributed so that an adversary, without colluding with other adversaries, cannot draw additional inferences about the private information, by linking together multiple pieces of information released to her. The assumption of no collusion is both reasonable and necessary in the above application domains that require release of private user information. SPARSI enables us to formally define privacy-aware data partitioning using the notion of sensitive properties for modeling private information and a hypergraph representation for describing the interdependencies between data entries and private information. We show that solving privacy-aware partitioning is, in general, NP-hard, but for specific information disclosure functions, good approximate solutions can be found using relaxation techniques. Finally, we present a local search algorithm applicable to generic information disclosure functions. We apply SPARSI together with the proposed algorithms on data from a real advertising scenario and show that we can partition data with no disclosure to any single advertiser.

cs.DB↗