Paper Group NANR 130
Decision Boundary Analysis of Adversarial Examples. Streaming Kernel PCA with \tilde{O}(\sqrt{n}) Random Features. Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems. Kawenn'on:nis: the Wordmaker for Kanyen’k'eha. Accelerating Greedy Coordinate Descent Methods. Eliminating Background-Bias for Robust Per …
Decision Boundary Analysis of Adversarial Examples
Title | Decision Boundary Analysis of Adversarial Examples |
Authors | Warren He, Bo Li, Dawn Song |
Abstract | Deep neural networks (DNNs) are vulnerable to adversarial examples, which are carefully crafted instances aiming to cause prediction errors for DNNs. Recent research on adversarial examples has examined local neighborhoods in the input space of DNN models. However, previous work has limited what regions to consider, focusing either on low-dimensional subspaces or small balls. In this paper, we argue that information from larger neighborhoods, such as from more directions and from greater distances, will better characterize the relationship between adversarial examples and the DNN models. First, we introduce an attack, OPTMARGIN, which generates adversarial examples robust to small perturbations. These examples successfully evade a defense that only considers a small ball around an input instance. Second, we analyze a larger neighborhood around input instances by looking at properties of surrounding decision boundaries, namely the distances to the boundaries and the adjacent classes. We find that the boundaries around these adversarial examples do not resemble the boundaries around benign examples. Finally, we show that, under scrutiny of the surrounding decision boundaries, our OPTMARGIN examples do not convincingly mimic benign examples. Although our experiments are limited to a few specific attacks, we hope these findings will motivate new, more evasive attacks and ultimately, effective defenses. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=BkpiPMbA- |
https://openreview.net/pdf?id=BkpiPMbA- | |
PWC | https://paperswithcode.com/paper/decision-boundary-analysis-of-adversarial |
Repo | |
Framework | |
Streaming Kernel PCA with \tilde{O}(\sqrt{n}) Random Features
Title | Streaming Kernel PCA with \tilde{O}(\sqrt{n}) Random Features |
Authors | Md Enayat Ullah, Poorya Mianjy, Teodor Vanislavov Marinov, Raman Arora |
Abstract | We study the statistical and computational aspects of kernel principal component analysis using random Fourier features and show that under mild assumptions, $O(\sqrt{n} \log n)$ features suffices to achieve $O(1/\epsilon^2)$ sample complexity. Furthermore, we give a memory efficient streaming algorithm based on classical Oja’s algorithm that achieves this rate |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7961-streaming-kernel-pca-with-tildeosqrtn-random-features |
http://papers.nips.cc/paper/7961-streaming-kernel-pca-with-tildeosqrtn-random-features.pdf | |
PWC | https://paperswithcode.com/paper/streaming-kernel-pca-with-tildeosqrtn-random-1 |
Repo | |
Framework | |
Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems
Title | Learning Pipelines with Limited Data and Domain Knowledge: A Study in Parsing Physics Problems |
Authors | Mrinmaya Sachan, Kumar Avinava Dubey, Tom M. Mitchell, Dan Roth, Eric P. Xing |
Abstract | As machine learning becomes more widely used in practice, we need new methods to build complex intelligent systems that integrate learning with existing software, and with domain knowledge encoded as rules. As a case study, we present such a system that learns to parse Newtonian physics problems in textbooks. This system, Nuts&Bolts, learns a pipeline process that incorporates existing code, pre-learned machine learning models, and human engineered rules. It jointly trains the entire pipeline to prevent propagation of errors, using a combination of labelled and unlabelled data. Our approach achieves a good performance on the parsing task, outperforming the simple pipeline and its variants. Finally, we also show how Nuts&Bolts can be used to achieve improvements on a relation extraction task and on the end task of answering Newtonian physics problems. |
Tasks | Relation Extraction |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7299-learning-pipelines-with-limited-data-and-domain-knowledge-a-study-in-parsing-physics-problems |
http://papers.nips.cc/paper/7299-learning-pipelines-with-limited-data-and-domain-knowledge-a-study-in-parsing-physics-problems.pdf | |
PWC | https://paperswithcode.com/paper/learning-pipelines-with-limited-data-and |
Repo | |
Framework | |
Kawenn'on:nis: the Wordmaker for Kanyen’k'eha
Title | Kawenn'on:nis: the Wordmaker for Kanyen’k'eha |
Authors | Anna Kazantseva, Owennatekha Brian Maracle, Ronkwe{'}tiy{'o}hstha Josiah Maracle, Aidan Pine |
Abstract | In this paper we describe preliminary work on Kawenn{'o}n:nis, a verb conjugator for Kanyen{'}k{'e}ha (Ohsweken dialect). The project is the result of a collaboration between Onkwawenna Kentyohkwa Kanyen{'}k{'e}ha immersion school and the Canadian National Research Council{'}s Indigenous Language Technology lab. The purpose of Kawenn{'o}n:nis is to build on the educational successes of the Onkwawenna Kentyohkwa school and develop a tool that assists students in learning how to conjugate verbs in Kanyen{'}k{'e}ha; a skill that is essential to mastering the language. Kawenn{'o}n:nis is implemented with both web and mobile front-ends that communicate with an application programming interface that in turn communicates with a symbolic language model implemented as a finite state transducer. Eventually, it will serve as a foundation for several other applications for both Kanyen{'}k{'e}ha and other Iroquoian languages. |
Tasks | Language Modelling |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4806/ |
https://www.aclweb.org/anthology/W18-4806 | |
PWC | https://paperswithcode.com/paper/kawenna3nnis-the-wordmaker-for-kanyenkaha |
Repo | |
Framework | |
Accelerating Greedy Coordinate Descent Methods
Title | Accelerating Greedy Coordinate Descent Methods |
Authors | Haihao Lu, Robert Freund, Vahab Mirrokni |
Abstract | We introduce and study two algorithms to accelerate greedy coordinate descent in theory and in practice: Accelerated Semi-Greedy Coordinate Descent (ASCD) and Accelerated Greedy Coordinate Descent (AGCD). On the theory side, our main results are for ASCD: we show that ASCD achieves $O(1/k^2)$ convergence, and it also achieves accelerated linear convergence for strongly convex functions. On the empirical side, while both AGCD and ASCD outperform Accelerated Randomized Coordinate Descent on most instances in our numerical experiments, we note that AGCD significantly outperforms the other two methods in our experiments, in spite of a lack of theoretical guarantees for this method. To complement this empirical finding for AGCD, we present an explanation why standard proof techniques for acceleration cannot work for AGCD, and we further introduce a technical condition under which AGCD is guaranteed to have accelerated convergence. Finally, we confirm that this technical condition holds in our numerical experiments. |
Tasks | |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2201 |
http://proceedings.mlr.press/v80/lu18b/lu18b.pdf | |
PWC | https://paperswithcode.com/paper/accelerating-greedy-coordinate-descent |
Repo | |
Framework | |
Eliminating Background-Bias for Robust Person Re-Identification
Title | Eliminating Background-Bias for Robust Person Re-Identification |
Authors | Maoqing Tian, Shuai Yi, Hongsheng Li, Shihua Li, Xuesen Zhang, Jianping Shi, Junjie Yan, Xiaogang Wang |
Abstract | Person re-identification is an important topic in intelligent surveillance and computer vision. It aims to accurately measure visual similarities between person images for determining whether two images correspond to the same person. State-of-the-art methods mainly utilize deep learning based approaches for learning visual features for describing person appearances. However, we observe that existing deep learning models are biased to capture too much relevance between background appearances of person images. We design a series of experiments with newly created datasets to validate the influence of background information. To solve the background bias problem, we propose a person-region guided pooling deep neural network based on human parsing maps to learn more discriminative person-part features, and propose to augment training data with person images with random background. Extensive experiments demonstrate the robustness and effectiveness of our proposed method. |
Tasks | Human Parsing, Person Re-Identification |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Tian_Eliminating_Background-Bias_for_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Tian_Eliminating_Background-Bias_for_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/eliminating-background-bias-for-robust-person |
Repo | |
Framework | |
Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments
Title | Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments |
Authors | Dario Stojanovski, Alex Fraser, er |
Abstract | Cross-sentence context can provide valuable information in Machine Translation and is critical for translation of anaphoric pronouns and for providing consistent translations. In this paper, we devise simple oracle experiments targeting coreference and coherence. Oracles are an easy way to evaluate the effect of different discourse-level phenomena in NMT using BLEU and eliminate the necessity to manually define challenge sets for this purpose. We propose two context-aware NMT models and compare them against models working on a concatenation of consecutive sentences. Concatenation models perform better, but are computationally expensive. We show that NMT models taking advantage of context oracle signals can achieve considerable gains in BLEU, of up to 7.02 BLEU for coreference and 1.89 BLEU for coherence on subtitles translation. Access to strong signals allows us to make clear comparisons between context-aware models. |
Tasks | Coreference Resolution, Language Modelling, Machine Translation |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-6306/ |
https://www.aclweb.org/anthology/W18-6306 | |
PWC | https://paperswithcode.com/paper/coreference-and-coherence-in-neural-machine |
Repo | |
Framework | |
Automatic Distractor Suggestion for Multiple-Choice Tests Using Concept Embeddings and Information Retrieval
Title | Automatic Distractor Suggestion for Multiple-Choice Tests Using Concept Embeddings and Information Retrieval |
Authors | Le An Ha, Victoria Yaneva |
Abstract | Developing plausible distractors (wrong answer options) when writing multiple-choice questions has been described as one of the most challenging and time-consuming parts of the item-writing process. In this paper we propose a fully automatic method for generating distractor suggestions for multiple-choice questions used in high-stakes medical exams. The system uses a question stem and the correct answer as an input and produces a list of suggested distractors ranked based on their similarity to the stem and the correct answer. To do this we use a novel approach of combining concept embeddings with information retrieval methods. We frame the evaluation as a prediction task where we aim to {``}predict{''} the human-produced distractors used in large sets of medical questions, i.e. if a distractor generated by our system is good enough it is likely to feature among the list of distractors produced by the human item-writers. The results reveal that combining concept embeddings with information retrieval approaches significantly improves the generation of plausible distractors and enables us to match around 1 in 5 of the human-produced distractors. The approach proposed in this paper is generalisable to all scenarios where the distractors refer to concepts. | |
Tasks | Information Retrieval |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/W18-0548/ |
https://www.aclweb.org/anthology/W18-0548 | |
PWC | https://paperswithcode.com/paper/automatic-distractor-suggestion-for-multiple |
Repo | |
Framework | |
Deep Learning of Graph Matching
Title | Deep Learning of Graph Matching |
Authors | Andrei Zanfir, Cristian Sminchisescu |
Abstract | The problem of graph matching under node and pair-wise constraints is fundamental in areas as diverse as combinatorial optimization, machine learning or computer vision, where representing both the relations between nodes and their neighborhood structure is essential. We present an end-to-end model that makes it possible to learn all parameters of the graph matching process, including the unary and pairwise node neighborhoods, represented as deep feature extraction hierarchies. The challenge is in the formulation of the different matrix computation layers of the model in a way that enables the consistent, efficient propagation of gradients in the complete pipeline from the loss function, through the combinatorial optimization layer solving the matching problem, and the feature extraction hierarchy. Our computer vision experiments and ablation studies on challenging datasets like PASCAL VOC keypoints, Sintel and CUB show that matching models refined end-to-end are superior to counterparts based on feature hierarchies trained for other problems. |
Tasks | Combinatorial Optimization, Graph Matching |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zanfir_Deep_Learning_of_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zanfir_Deep_Learning_of_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-of-graph-matching |
Repo | |
Framework | |
Selfie Video Stabilization
Title | Selfie Video Stabilization |
Authors | Jiyang Yu, Ravi Ramamoorthi |
Abstract | We propose a novel algorithm for stabilizing selfie videos. Our goal is to automatically generate stabilized video that has optimal smooth motion in the sense of both foreground and background. The key insight is that non-rigid foreground motion in selfie videos can be analyzed using a 3D face model, and background motion can be analyzed using optical flow. We use second derivative of temporal trajectory of selected pixels as the measure of smoothness. Our algorithm stabilizes selfie videos by minimizing the smoothness measure of the back-ground, regularized by the motion of the foreground. Experiments show that our method outperforms state-of-the-art general video stabilization techniques in selfie videos. |
Tasks | Optical Flow Estimation |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jiyang_Yu_Selfie_Video_Stabilization_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Jiyang_Yu_Selfie_Video_Stabilization_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/selfie-video-stabilization |
Repo | |
Framework | |
Using Data Mining to Predict Hospital Admissions From the Emergency Department
Title | Using Data Mining to Predict Hospital Admissions From the Emergency Department |
Authors | BYRON GRAHAM 1, RAYMOND BOND2, MICHAEL QUINN3, AND MAURICE MULVENNA2, (Senior Member, IEEE) |
Abstract | Crowding within emergency departments (EDs) can have signi cant negative consequences for patients. EDs therefore need to explore the use of innovative methods to improve patient ow and prevent overcrowding. One potential method is the use of data mining using machine learning techniques to predict ED admissions. This paper uses routinely collected administrative data (120 600 records) from two major acute hospitals in Northern Ireland to compare contrasting machine learning algorithms in predicting the risk of admission from the ED. We use three algorithms to build the predictive models: 1) logistic regression; 2) decision trees; and 3) gradient boosted machines (GBM). The GBM performed better (accuracy D 80:31%, AUC-ROC D 0:859) than the decision tree (accuracy D 80:06%, AUC-ROC D 0:824) and the logistic regression model (accuracy D 79:94%, AUC-ROC D 0:849). Drawing on logistic regression, we identify several factors related to hospital admissions, including hospital site, age, arrival mode, triage category, care group, previous admission in the past month, and previous admission in the past year. This paper highlights the potential utility of three common machine learning algorithms in predicting patient admissions. Practical implementation of the models developed in this paper in decision support tools would provide a snapshot of predicted admissions from the ED at a given time, allowing for advance resource planning and the avoidance bottlenecks in patient ow, as well as comparison of predicted and actual admission rates. When interpretability is a key consideration, EDs should consider adopting logistic regression models, although GBM’s will be useful where accuracy is paramount. |
Tasks | |
Published | 2018-02-22 |
URL | https://ieeexplore.ieee.org/document/8300528 |
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8300528 | |
PWC | https://paperswithcode.com/paper/using-data-mining-to-predict-hospital |
Repo | |
Framework | |
Forced Apart: Discovering Disentangled Representations Without Exhaustive Labels
Title | Forced Apart: Discovering Disentangled Representations Without Exhaustive Labels |
Authors | Alexey Romanov, Anna Rumshisky |
Abstract | Learning a better representation with neural networks is a challenging problem, which has been tackled from different perspectives in the past few years. In this work, we focus on learning a representation that would be useful in a clustering task. We introduce two novel loss components that substantially improve the quality of produced clusters, are simple to apply to arbitrary models and cost functions, and do not require a complicated training procedure. We perform an extensive set of experiments, supervised and unsupervised, and evaluate the proposed loss components on two most common types of models, Recurrent Neural Networks and Convolutional Neural Networks, showing that the approach we propose consistently improves the quality of KMeans clustering in terms of mutual information scores and outperforms previously proposed methods. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=S17mtzbRb |
https://openreview.net/pdf?id=S17mtzbRb | |
PWC | https://paperswithcode.com/paper/forced-apart-discovering-disentangled |
Repo | |
Framework | |
Learning to Infer
Title | Learning to Infer |
Authors | Joseph Marino, Yisong Yue, Stephan Mandt |
Abstract | Inference models, which replace an optimization-based inference procedure with a learned model, have been fundamental in advancing Bayesian deep learning, the most notable example being variational auto-encoders (VAEs). In this paper, we propose iterative inference models, which learn how to optimize a variational lower bound through repeatedly encoding gradients. Our approach generalizes VAEs under certain conditions, and by viewing VAEs in the context of iterative inference, we provide further insight into several recent empirical findings. We demonstrate the inference optimization capabilities of iterative inference models, explore unique aspects of these models, and show that they outperform standard inference models on typical benchmark data sets. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=B1Z3W-b0W |
https://openreview.net/pdf?id=B1Z3W-b0W | |
PWC | https://paperswithcode.com/paper/learning-to-infer |
Repo | |
Framework | |
Disambiguating False-Alarm Hashtag Usages in Tweets for Irony Detection
Title | Disambiguating False-Alarm Hashtag Usages in Tweets for Irony Detection |
Authors | Hen-Hsen Huang, Chiao-Chen Chen, Hsin-Hsi Chen |
Abstract | The reliability of self-labeled data is an important issue when the data are regarded as ground-truth for training and testing learning-based models. This paper addresses the issue of false-alarm hashtags in the self-labeled data for irony detection. We analyze the ambiguity of hashtag usages and propose a novel neural network-based model, which incorporates linguistic information from different aspects, to disambiguate the usage of three hashtags that are widely used to collect the training data for irony detection. Furthermore, we apply our model to prune the self-labeled training data. Experimental results show that the irony detection model trained on the less but cleaner training instances outperforms the models trained on all data. |
Tasks | Opinion Mining, Sentiment Analysis, Stance Detection |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-2122/ |
https://www.aclweb.org/anthology/P18-2122 | |
PWC | https://paperswithcode.com/paper/disambiguating-false-alarm-hashtag-usages-in |
Repo | |
Framework | |
MeSH-based dataset for measuring the relevance of text retrieval
Title | MeSH-based dataset for measuring the relevance of text retrieval |
Authors | Won Gyu Kim, Lana Yeganova, Donald Comeau, W John Wilbur, Zhiyong Lu |
Abstract | Creating simulated search environments has been of a significant interest in infor-mation retrieval, in both general and bio-medical search domains. Existing collec-tions include modest number of queries and are constructed by manually evaluat-ing retrieval results. In this work we pro-pose leveraging MeSH term assignments for creating synthetic test beds. We select a suitable subset of MeSH terms as queries, and utilize MeSH term assignments as pseudo-relevance rankings for retrieval evaluation. Using well studied retrieval functions, we show that their performance on the proposed data is consistent with similar findings in previous work. We further use the proposed retrieval evaluation framework to better understand how to combine heterogeneous sources of textual information. |
Tasks | Information Retrieval |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-2320/ |
https://www.aclweb.org/anthology/W18-2320 | |
PWC | https://paperswithcode.com/paper/mesh-based-dataset-for-measuring-the |
Repo | |
Framework | |