Paper Group ANR 651
Controlling for Unobserved Confounds in Classification Using Correlational Constraints. Columnar Database Techniques for Creating AI Features. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. Active Learning for Cost-Sensitive Classification. DataVizard: Recommending Visual Presentations for Structured Data. Un …
Controlling for Unobserved Confounds in Classification Using Correlational Constraints
| Title | Controlling for Unobserved Confounds in Classification Using Correlational Constraints |
| Authors | Virgile Landeiro, Aron Culotta |
| Abstract | As statistical classifiers become integrated into real-world applications, it is important to consider not only their accuracy but also their robustness to changes in the data distribution. In this paper, we consider the case where there is an unobserved confounding variable $z$ that influences both the features $\mathbf{x}$ and the class variable $y$. When the influence of $z$ changes from training to testing data, we find that the classifier accuracy can degrade rapidly. In our approach, we assume that we can predict the value of $z$ at training time with some error. The prediction for $z$ is then fed to Pearl’s back-door adjustment to build our model. Because of the attenuation bias caused by measurement error in $z$, standard approaches to controlling for $z$ are ineffective. In response, we propose a method to properly control for the influence of $z$ by first estimating its relationship with the class variable $y$, then updating predictions for $z$ to match that estimated relationship. By adjusting the influence of $z$, we show that we can build a model that exceeds competing baselines on accuracy as well as on robustness over a range of confounding relationships. |
| Tasks | |
| Published | 2017-03-05 |
| URL | http://arxiv.org/abs/1703.01671v2 |
| http://arxiv.org/pdf/1703.01671v2.pdf | |
| PWC | https://paperswithcode.com/paper/controlling-for-unobserved-confounds-in |
| Repo | |
| Framework | |
Columnar Database Techniques for Creating AI Features
| Title | Columnar Database Techniques for Creating AI Features |
| Authors | Brad Carlile, Akiko Marti, Guy Delamarter |
| Abstract | Recent advances with in-memory columnar database techniques have increased the performance of analytical queries on very large databases and data warehouses. At the same time, advances in artificial intelligence (AI) algorithms have increased the ability to analyze data. We use the term AI to encompass both Deep Learning (DL or neural network) and Machine Learning (ML aka Big Data analytics). Our exploration of the AI full stack has led us to a cross-stack columnar database innovation that efficiently creates features for AI analytics. The innovation is to create Augmented Dictionary Values (ADVs) to add to existing columnar database dictionaries in order to increase the efficiency of featurization by minimizing data movement and data duplication. We show how various forms of featurization (feature selection, feature extraction, and feature creation) can be efficiently calculated in a columnar database. The full stack AI investigation has also led us to propose an integrated columnar database and AI architecture. This architecture has information flows and feedback loops to improve the whole analytics cycle during multiple iterations of extracting data from the data sources, featurization, and analysis. |
| Tasks | Feature Selection |
| Published | 2017-12-07 |
| URL | http://arxiv.org/abs/1712.02882v1 |
| http://arxiv.org/pdf/1712.02882v1.pdf | |
| PWC | https://paperswithcode.com/paper/columnar-database-techniques-for-creating-ai |
| Repo | |
| Framework | |
Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies
| Title | Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies |
| Authors | Amir Sadeghian, Alexandre Alahi, Silvio Savarese |
| Abstract | The majority of existing solutions to the Multi-Target Tracking (MTT) problem do not combine cues in a coherent end-to-end fashion over a long period of time. However, we present an online method that encodes long-term temporal dependencies across multiple cues. One key challenge of tracking methods is to accurately track occluded targets or those which share similar appearance properties with surrounding objects. To address this challenge, we present a structure of Recurrent Neural Networks (RNN) that jointly reasons on multiple cues over a temporal window. We are able to correct many data association errors and recover observations from an occluded state. We demonstrate the robustness of our data-driven approach by tracking multiple targets using their appearance, motion, and even interactions. Our method outperforms previous works on multiple publicly available datasets including the challenging MOT benchmark. |
| Tasks | |
| Published | 2017-01-08 |
| URL | http://arxiv.org/abs/1701.01909v2 |
| http://arxiv.org/pdf/1701.01909v2.pdf | |
| PWC | https://paperswithcode.com/paper/tracking-the-untrackable-learning-to-track |
| Repo | |
| Framework | |
Active Learning for Cost-Sensitive Classification
| Title | Active Learning for Cost-Sensitive Classification |
| Authors | Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daume III, John Langford |
| Abstract | We design an active learning algorithm for cost-sensitive multiclass classification: problems where different errors have different costs. Our algorithm, COAL, makes predictions by regressing to each label’s cost and predicting the smallest. On a new example, it uses a set of regressors that perform well on past data to estimate possible costs for each label. It queries only the labels that could be the best, ignoring the sure losers. We prove COAL can be efficiently implemented for any regression family that admits squared loss optimization; it also enjoys strong guarantees with respect to predictive performance and labeling effort. We empirically compare COAL to passive learning and several active learning baselines, showing significant improvements in labeling effort and test cost on real-world datasets. |
| Tasks | Active Learning |
| Published | 2017-03-03 |
| URL | https://arxiv.org/abs/1703.01014v3 |
| https://arxiv.org/pdf/1703.01014v3.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-for-cost-sensitive |
| Repo | |
| Framework | |
DataVizard: Recommending Visual Presentations for Structured Data
| Title | DataVizard: Recommending Visual Presentations for Structured Data |
| Authors | Rema Ananthanarayanan, Pranay Kr. Lohia, Srikanta Bedathur |
| Abstract | Selecting the appropriate visual presentation of the data such that it preserves the semantics of the underlying data and at the same time provides an intuitive summary of the data is an important, often the final step of data analytics. Unfortunately, this is also a step involving significant human effort starting from selection of groups of columns in the structured results from analytics stages, to the selection of right visualization by experimenting with various alternatives. In this paper, we describe our \emph{DataVizard} system aimed at reducing this overhead by automatically recommending the most appropriate visual presentation for the structured result. Specifically, we consider the following two scenarios: first, when one needs to visualize the results of a structured query such as SQL; and the second, when one has acquired a data table with an associated short description (e.g., tables from the Web). Using a corpus of real-world database queries (and their results) and a number of statistical tables crawled from the Web, we show that DataVizard is capable of recommending visual presentations with high accuracy. We also present the results of a user survey that we conducted in order to assess user views of the suitability of the presented charts vis-a-vis the plain text captions of the data. |
| Tasks | |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.04971v1 |
| http://arxiv.org/pdf/1711.04971v1.pdf | |
| PWC | https://paperswithcode.com/paper/datavizard-recommending-visual-presentations |
| Repo | |
| Framework | |
Unsupervised Event Abstraction using Pattern Abstraction and Local Process Models
| Title | Unsupervised Event Abstraction using Pattern Abstraction and Local Process Models |
| Authors | Felix Mannhardt, Niek Tax |
| Abstract | Process mining analyzes business processes based on events stored in event logs. However, some recorded events may correspond to activities on a very low level of abstraction. When events are recorded on a too low level of granularity, process discovery methods tend to generate overgeneralizing process models. Grouping low-level events to higher level activities, i.e., event abstraction, can be used to discover better process models. Existing event abstraction methods are mainly based on common sub-sequences and clustering techniques. In this paper, we propose to first discover local process models and then use those models to lift the event log to a higher level of abstraction. Our conjecture is that process models discovered on the obtained high-level event log return process models of higher quality: their fitness and precision scores are more balanced. We show this with preliminary results on several real-life event logs. |
| Tasks | |
| Published | 2017-04-11 |
| URL | http://arxiv.org/abs/1704.03520v2 |
| http://arxiv.org/pdf/1704.03520v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-event-abstraction-using-pattern |
| Repo | |
| Framework | |
Improving Speech Related Facial Action Unit Recognition by Audiovisual Information Fusion
| Title | Improving Speech Related Facial Action Unit Recognition by Audiovisual Information Fusion |
| Authors | Zibo Meng, Shizhong Han, Ping Liu, Yan Tong |
| Abstract | It is challenging to recognize facial action unit (AU) from spontaneous facial displays, especially when they are accompanied by speech. The major reason is that the information is extracted from a single source, i.e., the visual channel, in the current practice. However, facial activity is highly correlated with voice in natural human communications. Instead of solely improving visual observations, this paper presents a novel audiovisual fusion framework, which makes the best use of visual and acoustic cues in recognizing speech-related facial AUs. In particular, a dynamic Bayesian network (DBN) is employed to explicitly model the semantic and dynamic physiological relationships between AUs and phonemes as well as measurement uncertainty. A pilot audiovisual AU-coded database has been collected to evaluate the proposed framework, which consists of a “clean” subset containing frontal faces under well controlled circumstances and a challenging subset with large head movements and occlusions. Experiments on this database have demonstrated that the proposed framework yields significant improvement in recognizing speech-related AUs compared to the state-of-the-art visual-based methods especially for those AUs whose visual observations are impaired during speech, and more importantly also outperforms feature-level fusion methods by explicitly modeling and exploiting physiological relationships between AUs and phonemes. |
| Tasks | Facial Action Unit Detection |
| Published | 2017-06-29 |
| URL | http://arxiv.org/abs/1706.10197v1 |
| http://arxiv.org/pdf/1706.10197v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-speech-related-facial-action-unit |
| Repo | |
| Framework | |
Comment on “Biologically inspired protection of deep networks from adversarial attacks”
| Title | Comment on “Biologically inspired protection of deep networks from adversarial attacks” |
| Authors | Wieland Brendel, Matthias Bethge |
| Abstract | A recent paper suggests that Deep Neural Networks can be protected from gradient-based adversarial perturbations by driving the network activations into a highly saturated regime. Here we analyse such saturated networks and show that the attacks fail due to numerical limitations in the gradient computations. A simple stabilisation of the gradient estimates enables successful and efficient attacks. Thus, it has yet to be shown that the robustness observed in highly saturated networks is not simply due to numerical limitations. |
| Tasks | |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01547v1 |
| http://arxiv.org/pdf/1704.01547v1.pdf | |
| PWC | https://paperswithcode.com/paper/comment-on-biologically-inspired-protection |
| Repo | |
| Framework | |
Predicting Privileged Information for Height Estimation
| Title | Predicting Privileged Information for Height Estimation |
| Authors | Nikolaos Sarafianos, Christophoros Nikou, Ioannis A. Kakadiaris |
| Abstract | In this paper, we propose a novel regression-based method for employing privileged information to estimate the height using human metrology. The actual values of the anthropometric measurements are difficult to estimate accurately using state-of-the-art computer vision algorithms. Hence, we use ratios of anthropometric measurements as features. Since many anthropometric measurements are not available at test time in real-life scenarios, we employ a learning using privileged information (LUPI) framework in a regression setup. Instead of using the LUPI paradigm for regression in its original form (i.e., \epsilon-SVR+), we train regression models that predict the privileged information at test time. The predictions are then used, along with observable features, to perform height estimation. Once the height is estimated, a mapping to classes is performed. We demonstrate that the proposed approach can estimate the height better and faster than the \epsilon-SVR+ algorithm and report results for different genders and quartiles of humans. |
| Tasks | |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02709v1 |
| http://arxiv.org/pdf/1702.02709v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-privileged-information-for-height |
| Repo | |
| Framework | |
Learning Semantics for Image Annotation
| Title | Learning Semantics for Image Annotation |
| Authors | Amara Tariq, Hassan Foroosh |
| Abstract | Image search and retrieval engines rely heavily on textual annotation in order to match word queries to a set of candidate images. A system that can automatically annotate images with meaningful text can be highly beneficial for such engines. Currently, the approaches to develop such systems try to establish relationships between keywords and visual features of images. In this paper, We make three main contributions to this area: (i) We transform this problem from the low-level keyword space to the high-level semantics space that we refer to as the “{\em image theme}", (ii) Instead of treating each possible keyword independently, we use latent Dirichlet allocation to learn image themes from the associated texts in a training phase. Images are then annotated with image themes rather than keywords, using a modified continuous relevance model, which takes into account the spatial coherence and the visual continuity among images of common theme. (iii) To achieve more coherent annotations among images of common theme, we have integrated ConceptNet in learning the semantics of images, and hence augment image descriptions beyond annotations provided by humans. Images are thus further annotated by a few most significant words of the prominent image theme. Our extensive experiments show that a coherent theme-based image annotation using high-level semantics results in improved precision and recall as compared with equivalent classical keyword annotation systems. |
| Tasks | Image Retrieval |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05102v1 |
| http://arxiv.org/pdf/1705.05102v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-semantics-for-image-annotation |
| Repo | |
| Framework | |
Logic Programming for an Introductory Computer Science Course for High School Students
| Title | Logic Programming for an Introductory Computer Science Course for High School Students |
| Authors | Timothy Yuen, Maritz Reyes, Yuanlin Zhang |
| Abstract | This paper investigates how high school students approach computing through an introductory computer science course situated in the Logic Programming (LP) paradigm. This study shows how novice students operate within the LP paradigm while engaging in foundational computing concepts and skills, and presents a case for LP as a viable paradigm choice for introductory CS courses. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.09248v1 |
| http://arxiv.org/pdf/1706.09248v1.pdf | |
| PWC | https://paperswithcode.com/paper/logic-programming-for-an-introductory |
| Repo | |
| Framework | |
“Having 2 hours to write a paper is fun!": Detecting Sarcasm in Numerical Portions of Text
| Title | “Having 2 hours to write a paper is fun!": Detecting Sarcasm in Numerical Portions of Text |
| Authors | Lakshya Kumar, Arpan Somani, Pushpak Bhattacharyya |
| Abstract | Sarcasm occurring due to the presence of numerical portions in text has been quoted as an error made by automatic sarcasm detection approaches in the past. We present a first study in detecting sarcasm in numbers, as in the case of the sentence ‘Love waking up at 4 am’. We analyze the challenges of the problem, and present Rule-based, Machine Learning and Deep Learning approaches to detect sarcasm in numerical portions of text. Our Deep Learning approach outperforms four past works for sarcasm detection and Rule-based and Machine learning approaches on a dataset of tweets, obtaining an F1-score of 0.93. This shows that special attention to text containing numbers may be useful to improve state-of-the-art in sarcasm detection. |
| Tasks | Sarcasm Detection |
| Published | 2017-09-06 |
| URL | http://arxiv.org/abs/1709.01950v1 |
| http://arxiv.org/pdf/1709.01950v1.pdf | |
| PWC | https://paperswithcode.com/paper/having-2-hours-to-write-a-paper-is-fun |
| Repo | |
| Framework | |
Variational Inference over Non-differentiable Cardiac Simulators using Bayesian Optimization
| Title | Variational Inference over Non-differentiable Cardiac Simulators using Bayesian Optimization |
| Authors | Adam McCarthy, Blanca Rodriguez, Ana Minchole |
| Abstract | Performing inference over simulators is generally intractable as their runtime means we cannot compute a marginal likelihood. We develop a likelihood-free inference method to infer parameters for a cardiac simulator, which replicates electrical flow through the heart to the body surface. We improve the fit of a state-of-the-art simulator to an electrocardiogram (ECG) recorded from a real patient. |
| Tasks | |
| Published | 2017-12-09 |
| URL | http://arxiv.org/abs/1712.03353v1 |
| http://arxiv.org/pdf/1712.03353v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-inference-over-non-differentiable |
| Repo | |
| Framework | |
Multi-Objective Non-parametric Sequential Prediction
| Title | Multi-Objective Non-parametric Sequential Prediction |
| Authors | Guy Uziel, Ran El-Yaniv |
| Abstract | Online-learning research has mainly been focusing on minimizing one objective function. In many real-world applications, however, several objective functions have to be considered simultaneously. Recently, an algorithm for dealing with several objective functions in the i.i.d. case has been presented. In this paper, we extend the multi-objective framework to the case of stationary and ergodic processes, thus allowing dependencies among observations. We first identify an asymptomatic lower bound for any prediction strategy and then present an algorithm whose predictions achieve the optimal solution while fulfilling any continuous and convex constraining criterion. |
| Tasks | |
| Published | 2017-03-05 |
| URL | http://arxiv.org/abs/1703.01680v3 |
| http://arxiv.org/pdf/1703.01680v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-non-parametric-sequential |
| Repo | |
| Framework | |
A Bayesian Clearing Mechanism for Combinatorial Auctions
| Title | A Bayesian Clearing Mechanism for Combinatorial Auctions |
| Authors | Gianluca Brero, Sébastien Lahaie |
| Abstract | We cast the problem of combinatorial auction design in a Bayesian framework in order to incorporate prior information into the auction process and minimize the number of rounds to convergence. We first develop a generative model of agent valuations and market prices such that clearing prices become maximum a posteriori estimates given observed agent valuations. This generative model then forms the basis of an auction process which alternates between refining estimates of agent valuations and computing candidate clearing prices. We provide an implementation of the auction using assumed density filtering to estimate valuations and expectation maximization to compute prices. An empirical evaluation over a range of valuation domains demonstrates that our Bayesian auction mechanism is highly competitive against the combinatorial clock auction in terms of rounds to convergence, even under the most favorable choices of price increment for this baseline. |
| Tasks | |
| Published | 2017-12-14 |
| URL | http://arxiv.org/abs/1712.05291v2 |
| http://arxiv.org/pdf/1712.05291v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-clearing-mechanism-for |
| Repo | |
| Framework | |
