Paper Group ANR 613
Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection. A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networks. From Propositional Logic to Plausible Reasoning: A Uniqueness Theorem. Per-instance Differential Privacy. When Point Process Meets RNNs: Predicting Fine-Grained User Interests with Mutual B …
Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
| Title | Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection |
| Authors | Guillermo Cabrera-Vives, Ignacio Reyes, Francisco Förster, Pablo A. Estévez, Juan-Carlos Maureira |
| Abstract | We introduce Deep-HiTS, a rotation invariant convolutional neural network (CNN) model for classifying images of transients candidates into artifacts or real sources for the High cadence Transient Survey (HiTS). CNNs have the advantage of learning the features automatically from the data while achieving high performance. We compare our CNN model against a feature engineering approach using random forests (RF). We show that our CNN significantly outperforms the RF model reducing the error by almost half. Furthermore, for a fixed number of approximately 2,000 allowed false transient candidates per night we are able to reduce the miss-classified real transients by approximately 1/5. To the best of our knowledge, this is the first time CNNs have been used to detect astronomical transient events. Our approach will be very useful when processing images from next generation instruments such as the Large Synoptic Survey Telescope (LSST). We have made all our code and data available to the community for the sake of allowing further developments and comparisons at https://github.com/guille-c/Deep-HiTS. |
| Tasks | Feature Engineering |
| Published | 2017-01-02 |
| URL | http://arxiv.org/abs/1701.00458v1 |
| http://arxiv.org/pdf/1701.00458v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-hits-rotation-invariant-convolutional |
| Repo | |
| Framework | |
A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networks
| Title | A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networks |
| Authors | Salman Ul Hassan Dar, Muzaffer Özbey, Ahmet Burak Çatlı, Tolga Çukur |
| Abstract | Purpose: Neural networks have received recent interest for reconstruction of undersampled MR acquisitions. Ideally network performance should be optimized by drawing the training and testing data from the same domain. In practice, however, large datasets comprising hundreds of subjects scanned under a common protocol are rare. The goal of this study is to introduce a transfer-learning approach to address the problem of data scarcity in training deep networks for accelerated MRI. Methods: Neural networks were trained on thousands of samples from public datasets of either natural images or brain MR images. The networks were then fine-tuned using only few tens of brain MR images in a distinct testing domain. Domain-transferred networks were compared to networks trained directly in the testing domain. Network performance was evaluated for varying acceleration factors (2-10), number of training samples (0.5-4k) and number of fine-tuning samples (0-100). Results: The proposed approach achieves successful domain transfer between MR images acquired with different contrasts (T1- and T2-weighted images), and between natural and MR images (ImageNet and T1- or T2-weighted images). Networks obtained via transfer-learning using only tens of images in the testing domain achieve nearly identical performance to networks trained directly in the testing domain using thousands of images. Conclusion: The proposed approach might facilitate the use of neural networks for MRI reconstruction without the need for collection of extensive imaging datasets. |
| Tasks | Transfer Learning |
| Published | 2017-10-07 |
| URL | https://arxiv.org/abs/1710.02615v3 |
| https://arxiv.org/pdf/1710.02615v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-transfer-learning-approach-for-accelerated |
| Repo | |
| Framework | |
From Propositional Logic to Plausible Reasoning: A Uniqueness Theorem
| Title | From Propositional Logic to Plausible Reasoning: A Uniqueness Theorem |
| Authors | Kevin S. Van Horn |
| Abstract | We consider the question of extending propositional logic to a logic of plausible reasoning, and posit four requirements that any such extension should satisfy. Each is a requirement that some property of classical propositional logic be preserved in the extended logic; as such, the requirements are simpler and less problematic than those used in Cox’s Theorem and its variants. As with Cox’s Theorem, our requirements imply that the extended logic must be isomorphic to (finite-set) probability theory. We also obtain specific numerical values for the probabilities, recovering the classical definition of probability as a theorem, with truth assignments that satisfy the premise playing the role of the “possible cases.” |
| Tasks | |
| Published | 2017-06-16 |
| URL | http://arxiv.org/abs/1706.05261v1 |
| http://arxiv.org/pdf/1706.05261v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-propositional-logic-to-plausible |
| Repo | |
| Framework | |
Per-instance Differential Privacy
| Title | Per-instance Differential Privacy |
| Authors | Yu-Xiang Wang |
| Abstract | We consider a refinement of differential privacy — per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard DP and inherits all its desirable properties, e.g., composition, invariance to side information and closedness to postprocessing, except that they all hold for every instance separately. When the data is drawn from a distribution, we show that per-instance DP implies generalization. Moreover, we provide explicit calculations of the per-instance DP for the output perturbation on a class of smooth learning problems. The result reveals an interesting and intuitive fact that an individual has stronger privacy if he/she has small “leverage score” with respect to the data set and if he/she can be predicted more accurately using the leave-one-out data set. Our simulation shows several orders-of-magnitude more favorable privacy and utility trade-off when we consider the privacy of only the users in the data set. In a case study on differentially private linear regression, provide a novel analysis of the One-Posterior-Sample (OPS) estimator and show that when the data set is well-conditioned it provides $(\epsilon,\delta)$-pDP for any target individuals and matches the exact lower bound up to a $1+\tilde{O}(n^{-1}\epsilon^{-2})$ multiplicative factor. We also demonstrate how we can use a “pDP to DP conversion” step to design AdaOPS which uses adaptive regularization to achieve the same results with $(\epsilon,\delta)$-DP. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07708v4 |
| http://arxiv.org/pdf/1707.07708v4.pdf | |
| PWC | https://paperswithcode.com/paper/per-instance-differential-privacy |
| Repo | |
| Framework | |
When Point Process Meets RNNs: Predicting Fine-Grained User Interests with Mutual Behavioral Infectivity
| Title | When Point Process Meets RNNs: Predicting Fine-Grained User Interests with Mutual Behavioral Infectivity |
| Authors | Tong Chen, Lin Wu, Yang Wang, Jun Zhang, Hongxu Chen, Xue Li |
| Abstract | Predicting fine-grained interests of users with temporal behavior is important to personalization and information filtering applications. However, existing interest prediction methods are incapable of capturing the subtle degreed user interests towards particular items, and the internal time-varying drifting attention of individuals is not studied yet. Moreover, the prediction process can also be affected by inter-personal influence, known as behavioral mutual infectivity. Inspired by point process in modeling temporal point process, in this paper we present a deep prediction method based on two recurrent neural networks (RNNs) to jointly model each user’s continuous browsing history and asynchronous event sequences in the context of inter-user behavioral mutual infectivity. Our model is able to predict the fine-grained interest from a user regarding a particular item and corresponding timestamps when an occurrence of event takes place. The proposed approach is more flexible to capture the dynamic characteristic of event sequences by using the temporal point process to model event data and timely update its intensity function by RNNs. Furthermore, to improve the interpretability of the model, the attention mechanism is introduced to emphasize both intra-personal and inter-personal behavior influence over time. Experiments on real datasets demonstrate that our model outperforms the state-of-the-art methods in fine-grained user interest prediction. |
| Tasks | |
| Published | 2017-10-14 |
| URL | http://arxiv.org/abs/1710.05135v2 |
| http://arxiv.org/pdf/1710.05135v2.pdf | |
| PWC | https://paperswithcode.com/paper/when-point-process-meets-rnns-predicting-fine |
| Repo | |
| Framework | |
Constructing a Hierarchical User Interest Structure based on User Profiles
| Title | Constructing a Hierarchical User Interest Structure based on User Profiles |
| Authors | Chao Zhao, Min Zhao, Yi Guan |
| Abstract | The interests of individual internet users fall into a hierarchical structure which is useful in regards to building personalized searches and recommendations. Most studies on this subject construct the interest hierarchy of a single person from the document perspective. In this study, we constructed the user interest hierarchy via user profiles. We organized 433,397 user interests, referred to here as “attentions”, into a user attention network (UAN) from 200 million user profiles; we then applied the Louvain algorithm to detect hierarchical clusters in these attentions. Finally, a 26-level hierarchy with 34,676 clusters was obtained. We found that these attention clusters were aggregated according to certain topics as opposed to the hyponymy-relation based conceptual ontologies. The topics can be entities or concepts, and the relations were not restrained by hyponymy. The concept relativity encapsulated in the user’s interest can be captured by labeling the attention clusters with corresponding concepts. |
| Tasks | |
| Published | 2017-09-20 |
| URL | http://arxiv.org/abs/1709.06918v1 |
| http://arxiv.org/pdf/1709.06918v1.pdf | |
| PWC | https://paperswithcode.com/paper/constructing-a-hierarchical-user-interest |
| Repo | |
| Framework | |
Unsupervised object discovery for instance recognition
| Title | Unsupervised object discovery for instance recognition |
| Authors | Oriane Siméoni, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum |
| Abstract | Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, that are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The descriptors derived from the salient regions improve particular object retrieval, most noticeably in a large collections containing small objects. |
| Tasks | Image Retrieval |
| Published | 2017-09-14 |
| URL | http://arxiv.org/abs/1709.04725v2 |
| http://arxiv.org/pdf/1709.04725v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-object-discovery-for-instance |
| Repo | |
| Framework | |
Trainable Referring Expression Generation using Overspecification Preferences
| Title | Trainable Referring Expression Generation using Overspecification Preferences |
| Authors | Thiago castro Ferreira, Ivandre Paraboni |
| Abstract | Referring expression generation (REG) models that use speaker-dependent information require a considerable amount of training data produced by every individual speaker, or may otherwise perform poorly. In this work we present a simple REG experiment that allows the use of larger training data sets by grouping speakers according to their overspecification preferences. Intrinsic evaluation shows that this method generally outperforms the personalised method found in previous work. |
| Tasks | |
| Published | 2017-04-12 |
| URL | http://arxiv.org/abs/1704.03693v1 |
| http://arxiv.org/pdf/1704.03693v1.pdf | |
| PWC | https://paperswithcode.com/paper/trainable-referring-expression-generation |
| Repo | |
| Framework | |
Learning Photography Aesthetics with Deep CNNs
| Title | Learning Photography Aesthetics with Deep CNNs |
| Authors | Gautam Malu, Raju S. Bapi, Bipin Indurkhya |
| Abstract | Automatic photo aesthetic assessment is a challenging artificial intelligence task. Existing computational approaches have focused on modeling a single aesthetic score or a class (good or bad), however these do not provide any details on why the photograph is good or bad, or which attributes contribute to the quality of the photograph. To obtain both accuracy and human interpretation of the score, we advocate learning the aesthetic attributes along with the prediction of the overall score. For this purpose, we propose a novel multitask deep convolution neural network, which jointly learns eight aesthetic attributes along with the overall aesthetic score. We report near human performance in the prediction of the overall aesthetic score. To understand the internal representation of these attributes in the learned model, we also develop the visualization technique using back propagation of gradients. These visualizations highlight the important image regions for the corresponding attributes, thus providing insights about model’s representation of these attributes. We showcase the diversity and complexity associated with different attributes through a qualitative analysis of the activation maps. |
| Tasks | |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.03981v1 |
| http://arxiv.org/pdf/1707.03981v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-photography-aesthetics-with-deep |
| Repo | |
| Framework | |
Stochastic Gradient Descent for Relational Logistic Regression via Partial Network Crawls
| Title | Stochastic Gradient Descent for Relational Logistic Regression via Partial Network Crawls |
| Authors | Jiasen Yang, Bruno Ribeiro, Jennifer Neville |
| Abstract | Research in statistical relational learning has produced a number of methods for learning relational models from large-scale network data. While these methods have been successfully applied in various domains, they have been developed under the unrealistic assumption of full data access. In practice, however, the data are often collected by crawling the network, due to proprietary access, limited resources, and privacy concerns. Recently, we showed that the parameter estimates for relational Bayes classifiers computed from network samples collected by existing network crawlers can be quite inaccurate, and developed a crawl-aware estimation method for such models (Yang, Ribeiro, and Neville, 2017). In this work, we extend the methodology to learning relational logistic regression models via stochastic gradient descent from partial network crawls, and show that the proposed method yields accurate parameter estimates and confidence intervals. |
| Tasks | Relational Reasoning |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07716v2 |
| http://arxiv.org/pdf/1707.07716v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-gradient-descent-for-relational |
| Repo | |
| Framework | |
Clustering under Local Stability: Bridging the Gap between Worst-Case and Beyond Worst-Case Analysis
| Title | Clustering under Local Stability: Bridging the Gap between Worst-Case and Beyond Worst-Case Analysis |
| Authors | Maria-Florina Balcan, Colin White |
| Abstract | Recently, there has been substantial interest in clustering research that takes a beyond worst-case approach to the analysis of algorithms. The typical idea is to design a clustering algorithm that outputs a near-optimal solution, provided the data satisfy a natural stability notion. For example, Bilu and Linial (2010) and Awasthi et al. (2012) presented algorithms that output near-optimal solutions, assuming the optimal solution is preserved under small perturbations to the input distances. A drawback to this approach is that the algorithms are often explicitly built according to the stability assumption and give no guarantees in the worst case; indeed, several recent algorithms output arbitrarily bad solutions even when just a small section of the data does not satisfy the given stability notion. In this work, we address this concern in two ways. First, we provide algorithms that inherit the worst-case guarantees of clustering approximation algorithms, while simultaneously guaranteeing near-optimal solutions when the data is stable. Our algorithms are natural modifications to existing state-of-the-art approximation algorithms. Second, we initiate the study of local stability, which is a property of a single optimal cluster rather than an entire optimal solution. We show our algorithms output all optimal clusters which satisfy stability locally. Specifically, we achieve strong positive results in our local framework under recent stability notions including metric perturbation resilience (Angelidakis et al. 2017) and robust perturbation resilience (Balcan and Liang 2012) for the $k$-median, $k$-means, and symmetric/asymmetric $k$-center objectives. |
| Tasks | |
| Published | 2017-05-19 |
| URL | http://arxiv.org/abs/1705.07157v1 |
| http://arxiv.org/pdf/1705.07157v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-under-local-stability-bridging-the |
| Repo | |
| Framework | |
A Generic Approach for Escaping Saddle points
| Title | A Generic Approach for Escaping Saddle points |
| Authors | Sashank J Reddi, Manzil Zaheer, Suvrit Sra, Barnabas Poczos, Francis Bach, Ruslan Salakhutdinov, Alexander J Smola |
| Abstract | A central challenge to using first-order methods for optimizing nonconvex problems is the presence of saddle points. First-order methods often get stuck at saddle points, greatly deteriorating their performance. Typically, to escape from saddles one has to use second-order methods. However, most works on second-order methods rely extensively on expensive Hessian-based computations, making them impractical in large-scale settings. To tackle this challenge, we introduce a generic framework that minimizes Hessian based computations while at the same time provably converging to second-order critical points. Our framework carefully alternates between a first-order and a second-order subroutine, using the latter only close to saddle points, and yields convergence results competitive to the state-of-the-art. Empirical results suggest that our strategy also enjoys a good practical performance. |
| Tasks | |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01434v1 |
| http://arxiv.org/pdf/1709.01434v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generic-approach-for-escaping-saddle-points |
| Repo | |
| Framework | |
Baselines and test data for cross-lingual inference
| Title | Baselines and test data for cross-lingual inference |
| Authors | Željko Agić, Natalie Schluter |
| Abstract | The recent years have seen a revival of interest in textual entailment, sparked by i) the emergence of powerful deep neural network learners for natural language processing and ii) the timely development of large-scale evaluation datasets such as SNLI. Recast as natural language inference, the problem now amounts to detecting the relation between pairs of statements: they either contradict or entail one another, or they are mutually neutral. Current research in natural language inference is effectively exclusive to English. In this paper, we propose to advance the research in SNLI-style natural language inference toward multilingual evaluation. To that end, we provide test data for four major languages: Arabic, French, Spanish, and Russian. We experiment with a set of baselines. Our systems are based on cross-lingual word embeddings and machine translation. While our best system scores an average accuracy of just over 75%, we focus largely on enabling further research in multilingual inference. |
| Tasks | Machine Translation, Natural Language Inference, Word Embeddings |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05347v2 |
| http://arxiv.org/pdf/1704.05347v2.pdf | |
| PWC | https://paperswithcode.com/paper/baselines-and-test-data-for-cross-lingual |
| Repo | |
| Framework | |
Automatic Detection of Fake News
| Title | Automatic Detection of Fake News |
| Authors | Verónica Pérez-Rosas, Bennett Kleinberg, Alexandra Lefevre, Rada Mihalcea |
| Abstract | The proliferation of misleading information in everyday access media outlets such as social media feeds, news blogs, and online newspapers have made it challenging to identify trustworthy news sources, thus increasing the need for computational tools able to provide insights into the reliability of online content. In this paper, we focus on the automatic identification of fake content in online news. Our contribution is twofold. First, we introduce two novel datasets for the task of fake news detection, covering seven different news domains. We describe the collection, annotation, and validation process in detail and present several exploratory analysis on the identification of linguistic differences in fake and legitimate news content. Second, we conduct a set of learning experiments to build accurate fake news detectors. In addition, we provide comparative analyses of the automatic and manual identification of fake news. |
| Tasks | Fake News Detection |
| Published | 2017-08-23 |
| URL | http://arxiv.org/abs/1708.07104v1 |
| http://arxiv.org/pdf/1708.07104v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-detection-of-fake-news |
| Repo | |
| Framework | |
ViP-CNN: Visual Phrase Guided Convolutional Neural Network
| Title | ViP-CNN: Visual Phrase Guided Convolutional Neural Network |
| Authors | Yikang Li, Wanli Ouyang, Xiaogang Wang, Xiao’ou Tang |
| Abstract | As the intermediate level task connecting image captioning and object detection, visual relationship detection started to catch researchers’ attention because of its descriptive power and clear structure. It detects the objects and captures their pair-wise interactions with a subject-predicate-object triplet, e.g. person-ride-horse. In this paper, each visual relationship is considered as a phrase with three components. We formulate the visual relationship detection as three inter-connected recognition problems and propose a Visual Phrase guided Convolutional Neural Network (ViP-CNN) to address them simultaneously. In ViP-CNN, we present a Phrase-guided Message Passing Structure (PMPS) to establish the connection among relationship components and help the model consider the three problems jointly. Corresponding non-maximum suppression method and model training strategy are also proposed. Experimental results show that our ViP-CNN outperforms the state-of-art method both in speed and accuracy. We further pretrain ViP-CNN on our cleansed Visual Genome Relationship dataset, which is found to perform better than the pretraining on the ImageNet for this task. |
| Tasks | Image Captioning, Object Detection |
| Published | 2017-02-23 |
| URL | http://arxiv.org/abs/1702.07191v2 |
| http://arxiv.org/pdf/1702.07191v2.pdf | |
| PWC | https://paperswithcode.com/paper/vip-cnn-visual-phrase-guided-convolutional |
| Repo | |
| Framework | |
