July 29, 2019

2999 words 15 mins read

Paper Group ANR 133

An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks. Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes. Win Prediction in Esports: Mixed-Rank Match Prediction in Multi-player Online Battle Arena Games. Novel Framework for Spectral Clustering using Topological Node Featur …

An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks


Title	An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks
Authors	Mateusz Koziński, Loïc Simon, Frédéric Jurie
Abstract	We propose a method for semi-supervised training of structured-output neural networks. Inspired by the framework of Generative Adversarial Networks (GAN), we train a discriminator network to capture the notion of a quality of network output. To this end, we leverage the qualitative difference between outputs obtained on the labelled training data and unannotated data. We then use the discriminator as a source of error signal for unlabelled data. This effectively boosts the performance of a network on a held out test set. Initial experiments in image segmentation demonstrate that the proposed framework enables achieving the same network performance as in a fully supervised scenario, while using two times less annotations.
Tasks	Semantic Segmentation
Published	2017-02-08
URL	http://arxiv.org/abs/1702.02382v1
PDF	http://arxiv.org/pdf/1702.02382v1.pdf
PWC	https://paperswithcode.com/paper/an-adversarial-regularisation-for-semi
Repo
Framework

Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes


Title	Joint Intermodal and Intramodal Label Transfers for Extremely Rare or Unseen Classes
Authors	Guo-Jun Qi, Wei Liu, Charu Aggarwal, Thomas Huang
Abstract	In this paper, we present a label transfer model from texts to images for image classification tasks. The problem of image classification is often much more challenging than text classification. On one hand, labeled text data is more widely available than the labeled images for classification tasks. On the other hand, text data tends to have natural semantic interpretability, and they are often more directly related to class labels. On the contrary, the image features are not directly related to concepts inherent in class labels. One of our goals in this paper is to develop a model for revealing the functional relationships between text and image features as to directly transfer intermodal and intramodal labels to annotate the images. This is implemented by learning a transfer function as a bridge to propagate the labels between two multimodal spaces. However, the intermodal label transfers could be undermined by blindly transferring the labels of noisy texts to annotate images. To mitigate this problem, we present an intramodal label transfer process, which complements the intermodal label transfer by transferring the image labels instead when relevant text is absent from the source corpus. In addition, we generalize the inter-modal label transfer to zero-shot learning scenario where there are only text examples available to label unseen classes of images without any positive image examples. We evaluate our algorithm on an image classification task and show the effectiveness with respect to the other compared algorithms.
Tasks	Image Classification, Text Classification, Zero-Shot Learning
Published	2017-03-22
URL	http://arxiv.org/abs/1703.07519v1
PDF	http://arxiv.org/pdf/1703.07519v1.pdf
PWC	https://paperswithcode.com/paper/joint-intermodal-and-intramodal-label
Repo
Framework

Win Prediction in Esports: Mixed-Rank Match Prediction in Multi-player Online Battle Arena Games


Title	Win Prediction in Esports: Mixed-Rank Match Prediction in Multi-player Online Battle Arena Games
Authors	Victoria Hodge, Sam Devlin, Nick Sephton, Florian Block, Anders Drachen, Peter Cowling
Abstract	Esports has emerged as a popular genre for players as well as spectators, supporting a global entertainment industry. Esports analytics has evolved to address the requirement for data-driven feedback, and is focused on cyber-athlete evaluation, strategy and prediction. Towards the latter, previous work has used match data from a variety of player ranks from hobbyist to professional players. However, professional players have been shown to behave differently than lower ranked players. Given the comparatively limited supply of professional data, a key question is thus whether mixed-rank match datasets can be used to create data-driven models which predict winners in professional matches and provide a simple in-game statistic for viewers and broadcasters. Here we show that, although there is a slightly reduced accuracy, mixed-rank datasets can be used to predict the outcome of professional matches, with suitably optimized configurations.
Tasks
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06498v1
PDF	http://arxiv.org/pdf/1711.06498v1.pdf
PWC	https://paperswithcode.com/paper/win-prediction-in-esports-mixed-rank-match
Repo
Framework

Novel Framework for Spectral Clustering using Topological Node Features(TNF)


Title	Novel Framework for Spectral Clustering using Topological Node Features(TNF)
Authors	Lalith Srikanth Chintalapati, Raghunatha Sarma Rachakonda
Abstract	Spectral clustering has gained importance in recent years due to its ability to cluster complex data as it requires only pairwise similarity among data points with its ease of implementation. The central point in spectral clustering is the process of capturing pair-wise similarity. In the literature, many research techniques have been proposed for effective construction of affinity matrix with suitable pair- wise similarity. In this paper a general framework for capturing pairwise affinity using local features such as density, proximity and structural similarity is been proposed. Topological Node Features are exploited to define the notion of density and local structure. These local features are incorporated into the construction of the affinity matrix. Experimental results, on widely used datasets such as synthetic shape datasets, UCI real datasets and MNIST handwritten datasets show that the proposed framework outperforms standard spectral clustering methods.
Tasks
Published	2017-03-31
URL	http://arxiv.org/abs/1703.10756v2
PDF	http://arxiv.org/pdf/1703.10756v2.pdf
PWC	https://paperswithcode.com/paper/novel-framework-for-spectral-clustering-using
Repo
Framework

Arrays of (locality-sensitive) Count Estimators (ACE): High-Speed Anomaly Detection via Cache Lookups


Title	Arrays of (locality-sensitive) Count Estimators (ACE): High-Speed Anomaly Detection via Cache Lookups
Authors	Chen Luo, Anshumali Shrivastava
Abstract	Anomaly detection is one of the frequent and important subroutines deployed in large-scale data processing systems. Even being a well-studied topic, existing techniques for unsupervised anomaly detection require storing significant amounts of data, which is prohibitive from memory and latency perspective. In the big-data world existing methods fail to address the new set of memory and latency constraints. In this paper, we propose ACE (Arrays of (locality-sensitive) Count Estimators) algorithm that can be 60x faster than the ELKI package~\cite{DBLP:conf/ssd/AchtertBKSZ09}, which has the fastest implementation of the unsupervised anomaly detection algorithms. ACE algorithm requires less than $4MB$ memory, to dynamically compress the full data information into a set of count arrays. These tiny $4MB$ arrays of counts are sufficient for unsupervised anomaly detection. At the core of the ACE algorithm, there is a novel statistical estimator which is derived from the sampling view of Locality Sensitive Hashing(LSH). This view is significantly different and efficient than the widely popular view of LSH for near-neighbor search. We show the superiority of ACE algorithm over 11 popular baselines on 3 benchmark datasets, including the KDD-Cup99 data which is the largest available benchmark comprising of more than half a million entries with ground truth anomaly labels.
Tasks	Anomaly Detection, Unsupervised Anomaly Detection
Published	2017-06-20
URL	http://arxiv.org/abs/1706.06664v1
PDF	http://arxiv.org/pdf/1706.06664v1.pdf
PWC	https://paperswithcode.com/paper/arrays-of-locality-sensitive-count-estimators
Repo
Framework

Cost-Effective Active Learning for Deep Image Classification


Title	Cost-Effective Active Learning for Deep Image Classification
Authors	Keze Wang, Dongyu Zhang, Ya Li, Ruimao Zhang, Liang Lin
Abstract	Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing active learning methods in two aspects. First, we incorporate deep convolutional neural networks into active learning. Through the properly designed framework, the feature representation and the classifier can be simultaneously updated with progressively annotated informative samples. Second, we present a cost-effective sample selection strategy to improve the classification performance with less manual annotations. Unlike traditional methods focusing on only the uncertain samples of low prediction confidence, we especially discover the large amount of high confidence samples from the unlabeled set for feature learning. Specifically, these high confidence samples are automatically selected and iteratively assigned pseudo-labels. We thus call our framework “Cost-Effective Active Learning” (CEAL) standing for the two advantages.Extensive experiments demonstrate that the proposed CEAL framework can achieve promising results on two challenging image classification datasets, i.e., face recognition on CACD database [1] and object categorization on Caltech-256 [2].
Tasks	Active Learning, Face Recognition, Image Classification
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03551v1
PDF	http://arxiv.org/pdf/1701.03551v1.pdf
PWC	https://paperswithcode.com/paper/cost-effective-active-learning-for-deep-image
Repo
Framework

Jointly Learning Word Embeddings and Latent Topics


Title	Jointly Learning Word Embeddings and Latent Topics
Authors	Bei Shi, Wai Lam, Shoaib Jameel, Steven Schockaert, Kwun Ping Lai
Abstract	Word embedding models such as Skip-gram learn a vector-space representation for each word, based on the local word collocation patterns that are observed in a text corpus. Latent topic models, on the other hand, take a more global view, looking at the word distributions across the corpus to assign a topic to each word occurrence. These two paradigms are complementary in how they represent the meaning of word occurrences. While some previous works have already looked at using word embeddings for improving the quality of latent topics, and conversely, at using latent topics for improving word embeddings, such “two-step” methods cannot capture the mutual interaction between the two paradigms. In this paper, we propose STE, a framework which can learn word embeddings and latent topics in a unified manner. STE naturally obtains topic-specific word embeddings, and thus addresses the issue of polysemy. At the same time, it also learns the term distributions of the topics, and the topic distributions of the documents. Our experimental results demonstrate that the STE model can indeed generate useful topic-specific word embeddings and coherent latent topics in an effective and efficient way.
Tasks	Learning Word Embeddings, Topic Models, Word Embeddings
Published	2017-06-21
URL	http://arxiv.org/abs/1706.07276v1
PDF	http://arxiv.org/pdf/1706.07276v1.pdf
PWC	https://paperswithcode.com/paper/jointly-learning-word-embeddings-and-latent
Repo
Framework

Latent Laplacian Maximum Entropy Discrimination for Detection of High-Utility Anomalies


Title	Latent Laplacian Maximum Entropy Discrimination for Detection of High-Utility Anomalies
Authors	Elizabeth Hou, Kumar Sricharan, Alfred O. Hero
Abstract	Data-driven anomaly detection methods suffer from the drawback of detecting all instances that are statistically rare, irrespective of whether the detected instances have real-world significance or not. In this paper, we are interested in the problem of specifically detecting anomalous instances that are known to have high real-world utility, while ignoring the low-utility statistically anomalous instances. To this end, we propose a novel method called Latent Laplacian Maximum Entropy Discrimination (LatLapMED) as a potential solution. This method uses the EM algorithm to simultaneously incorporate the Geometric Entropy Minimization principle for identifying statistical anomalies, and the Maximum Entropy Discrimination principle to incorporate utility labels, in order to detect high-utility anomalies. We apply our method in both simulated and real datasets to demonstrate that it has superior performance over existing alternatives that independently pre-process with unsupervised anomaly detection algorithms before classifying.
Tasks	Anomaly Detection, Unsupervised Anomaly Detection
Published	2017-02-16
URL	http://arxiv.org/abs/1702.05148v3
PDF	http://arxiv.org/pdf/1702.05148v3.pdf
PWC	https://paperswithcode.com/paper/latent-laplacian-maximum-entropy
Repo
Framework

Topology Adaptive Graph Convolutional Networks


Title	Topology Adaptive Graph Convolutional Networks
Authors	Jian Du, Shanghang Zhang, Guanhang Wu, Jose M. F. Moura, Soummya Kar
Abstract	Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convolutional network (TAGCN), a novel graph convolutional network defined in the vertex domain. We provide a systematic way to design a set of fixed-size learnable filters to perform convolutions on graphs. The topologies of these filters are adaptive to the topology of the graph when they scan the graph to perform convolution. The TAGCN not only inherits the properties of convolutions in CNN for grid-structured data, but it is also consistent with convolution as defined in graph signal processing. Since no approximation to the convolution is needed, TAGCN exhibits better performance than existing spectral CNNs on a number of data sets and is also computationally simpler than other recent methods.
Tasks
Published	2017-10-28
URL	http://arxiv.org/abs/1710.10370v5
PDF	http://arxiv.org/pdf/1710.10370v5.pdf
PWC	https://paperswithcode.com/paper/topology-adaptive-graph-convolutional
Repo
Framework

Theory of Deep Learning III: explaining the non-overfitting puzzle


Title	Theory of Deep Learning III: explaining the non-overfitting puzzle
Authors	Tomaso Poggio, Kenji Kawaguchi, Qianli Liao, Brando Miranda, Lorenzo Rosasco, Xavier Boix, Jack Hidary, Hrushikesh Mhaskar
Abstract	A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics associated to gradient descent minimization of nonlinear networks is topologically equivalent, near the asymptotically stable minima of the empirical error, to linear gradient system in a quadratic potential with a degenerate (for square loss) or almost degenerate (for logistic or crossentropy loss) Hessian. The proposition depends on the qualitative theory of dynamical systems and is supported by numerical results. Our main propositions extend to deep nonlinear networks two properties of gradient descent for linear networks, that have been recently established (1) to be key to their generalization properties: 1. Gradient descent enforces a form of implicit regularization controlled by the number of iterations, and asymptotically converges to the minimum norm solution for appropriate initial conditions of gradient descent. This implies that there is usually an optimum early stopping that avoids overfitting of the loss. This property, valid for the square loss and many other loss functions, is relevant especially for regression. 2. For classification, the asymptotic convergence to the minimum norm solution implies convergence to the maximum margin solution which guarantees good classification error for “low noise” datasets. This property holds for loss functions such as the logistic and cross-entropy loss independently of the initial conditions. The robustness to overparametrization has suggestive implications for the robustness of the architecture of deep convolutional networks with respect to the curse of dimensionality.
Tasks
Published	2017-12-30
URL	http://arxiv.org/abs/1801.00173v2
PDF	http://arxiv.org/pdf/1801.00173v2.pdf
PWC	https://paperswithcode.com/paper/theory-of-deep-learning-iii-explaining-the
Repo
Framework

On Inconsistency Indices and Inconsistency Axioms in Pairwise Comparisons


Title	On Inconsistency Indices and Inconsistency Axioms in Pairwise Comparisons
Authors	Jiri Mazurek
Abstract	Pairwise comparisons are an important tool of modern (multiple criteria) decision making. Since human judgments are often inconsistent, many studies focused on the ways how to express and measure this inconsistency, and several inconsistency indices were proposed as an alternative to Saaty inconsistency index and inconsistency ratio for reciprocal pairwise comparisons matrices. This paper aims to: firstly, introduce a new measure of inconsistency of pairwise comparisons and to prove its basic properties; secondly, to postulate an additional axiom, an upper boundary axiom, to an existing set of axioms; and the last, but not least, the paper provides proofs of satisfaction of this additional axiom by selected inconsistency indices as well as it provides their numerical comparison.
Tasks	Decision Making
Published	2017-03-15
URL	http://arxiv.org/abs/1703.05204v2
PDF	http://arxiv.org/pdf/1703.05204v2.pdf
PWC	https://paperswithcode.com/paper/on-inconsistency-indices-and-inconsistency
Repo
Framework

word2vec Skip-Gram with Negative Sampling is a Weighted Logistic PCA


Title	word2vec Skip-Gram with Negative Sampling is a Weighted Logistic PCA
Authors	Andrew J. Landgraf, Jeremy Bellay
Abstract	We show that the skip-gram formulation of word2vec trained with negative sampling is equivalent to a weighted logistic PCA. This connection allows us to better understand the objective, compare it to other word embedding methods, and extend it to higher dimensional models.
Tasks
Published	2017-05-27
URL	http://arxiv.org/abs/1705.09755v1
PDF	http://arxiv.org/pdf/1705.09755v1.pdf
PWC	https://paperswithcode.com/paper/word2vec-skip-gram-with-negative-sampling-is
Repo
Framework

Data-Mining Textual Responses to Uncover Misconception Patterns


Title	Data-Mining Textual Responses to Uncover Misconception Patterns
Authors	Joshua J. Michalenko, Andrew S. Lan, Richard G. Baraniuk
Abstract	An important, yet largely unstudied, problem in student data analysis is to detect misconceptions from students’ responses to open-response questions. Misconception detection enables instructors to deliver more targeted feedback on the misconceptions exhibited by many students in their class, thus improving the quality of instruction. In this paper, we propose a new natural language processing-based framework to detect the common misconceptions among students’ textual responses to short-answer questions. We propose a probabilistic model for students’ textual responses involving misconceptions and experimentally validate it on a real-world student-response dataset. Experimental results show that our proposed framework excels at classifying whether a response exhibits one or more misconceptions. More importantly, it can also automatically detect the common misconceptions exhibited across responses from multiple students to multiple questions; this property is especially important at large scale, since instructors will no longer need to manually specify all possible misconceptions that students might exhibit.
Tasks
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08544v2
PDF	http://arxiv.org/pdf/1703.08544v2.pdf
PWC	https://paperswithcode.com/paper/data-mining-textual-responses-to-uncover
Repo
Framework

AVEID: Automatic Video System for Measuring Engagement In Dementia


Title	AVEID: Automatic Video System for Measuring Engagement In Dementia
Authors	Viral Parekh, Pin Sym Foong, Shendong Zhao, Ramanathan Subramanian
Abstract	Engagement in dementia is typically measured using behavior observational scales (BOS) that are tedious and involve intensive manual labor to annotate, and are therefore not easily scalable. We propose AVEID, a low cost and easy-to-use video-based engagement measurement tool to determine the engagement level of a person with dementia (PwD) during digital interaction. We show that the objective behavioral measures computed via AVEID correlate well with subjective expert impressions for the popular MPES and OME BOS, confirming its viability and effectiveness. Moreover, AVEID measures can be obtained for a variety of engagement designs, thereby facilitating large-scale studies with PwD populations.
Tasks
Published	2017-12-21
URL	http://arxiv.org/abs/1712.08084v1
PDF	http://arxiv.org/pdf/1712.08084v1.pdf
PWC	https://paperswithcode.com/paper/aveid-automatic-video-system-for-measuring
Repo
Framework

Precision Learning: Towards Use of Known Operators in Neural Networks


Title	Precision Learning: Towards Use of Known Operators in Neural Networks
Authors	Andreas Maier, Frank Schebesch, Christopher Syben, Tobias Würfl, Stefan Steidl, Jang-Hwan Choi, Rebecca Fahrig
Abstract	In this paper, we consider the use of prior knowledge within neural networks. In particular, we investigate the effect of a known transform within the mapping from input data space to the output domain. We demonstrate that use of known transforms is able to change maximal error bounds. In order to explore the effect further, we consider the problem of X-ray material decomposition as an example to incorporate additional prior knowledge. We demonstrate that inclusion of a non-linear function known from the physical properties of the system is able to reduce prediction errors therewith improving prediction quality from SSIM values of 0.54 to 0.88. This approach is applicable to a wide set of applications in physics and signal processing that provide prior knowledge on such transforms. Also maximal error estimation and network understanding could be facilitated within the context of precision learning.
Tasks
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00374v4
PDF	http://arxiv.org/pdf/1712.00374v4.pdf
PWC	https://paperswithcode.com/paper/precision-learning-towards-use-of-known
Repo
Framework