Paper Group ANR 962
An Application of HodgeRank to Online Peer Assessment. Ensemble Kalman Filtering for Online Gaussian Process Regression and Learning. Think Visually: Question Answering through Virtual Imagery. Investigations on Knowledge Base Embedding for Relation Prediction and Extraction. On Coresets for Logistic Regression. The role of grammar in transition-pr …
An Application of HodgeRank to Online Peer Assessment
| Title | An Application of HodgeRank to Online Peer Assessment |
| Authors | Tse-Yu Lin, Yen-Lung Tsai |
| Abstract | Bias and heterogeneity in peer assessment can lead to the issue of unfair scoring in the educational field. To deal with this problem, we propose a reference ranking method for an online peer assessment system using HodgeRank. Such a scheme provides instructors with an objective scoring reference based on mathematics. |
| Tasks | |
| Published | 2018-03-07 |
| URL | http://arxiv.org/abs/1803.02509v1 |
| http://arxiv.org/pdf/1803.02509v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-application-of-hodgerank-to-online-peer |
| Repo | |
| Framework | |
Ensemble Kalman Filtering for Online Gaussian Process Regression and Learning
| Title | Ensemble Kalman Filtering for Online Gaussian Process Regression and Learning |
| Authors | Danil Kuzin, Le Yang, Olga Isupova, Lyudmila Mihaylova |
| Abstract | Gaussian process regression is a machine learning approach which has been shown its power for estimation of unknown functions. However, Gaussian processes suffer from high computational complexity, as in a basic form they scale cubically with the number of observations. Several approaches based on inducing points were proposed to handle this problem in a static context. These methods though face challenges with real-time tasks and when the data is received sequentially over time. In this paper, a novel online algorithm for training sparse Gaussian process models is presented. It treats the mean and hyperparameters of the Gaussian process as the state and parameters of the ensemble Kalman filter, respectively. The online evaluation of the parameters and the state is performed on new upcoming samples of data. This procedure iteratively improves the accuracy of parameter estimates. The ensemble Kalman filter reduces the computational complexity required to obtain predictions with Gaussian processes preserving the accuracy level of these predictions. The performance of the proposed method is demonstrated on the synthetic dataset and real large dataset of UK house prices. |
| Tasks | Gaussian Processes |
| Published | 2018-07-09 |
| URL | http://arxiv.org/abs/1807.03369v1 |
| http://arxiv.org/pdf/1807.03369v1.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-kalman-filtering-for-online-gaussian |
| Repo | |
| Framework | |
Think Visually: Question Answering through Virtual Imagery
| Title | Think Visually: Question Answering through Virtual Imagery |
| Authors | Ankit Goyal, Jian Wang, Jia Deng |
| Abstract | In this paper, we study the problem of geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture designed for answering questions that admit latent visual representations. DSMN learns to generate and reason over such representations. Further, we propose two synthetic benchmarks, FloorPlanQA and ShapeIntersection, to evaluate the geometric reasoning capability of QA systems. Experimental results validate the effectiveness of our proposed DSMN for visual thinking tasks. |
| Tasks | Question Answering |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.11025v1 |
| http://arxiv.org/pdf/1805.11025v1.pdf | |
| PWC | https://paperswithcode.com/paper/think-visually-question-answering-through |
| Repo | |
| Framework | |
Investigations on Knowledge Base Embedding for Relation Prediction and Extraction
| Title | Investigations on Knowledge Base Embedding for Relation Prediction and Extraction |
| Authors | Peng Xu, Denilson Barbosa |
| Abstract | We report an evaluation of the effectiveness of the existing knowledge base embedding models for relation prediction and for relation extraction on a wide range of benchmarks. We also describe a new benchmark, which is much larger and complex than previous ones, which we introduce to help validate the effectiveness of both tasks. The results demonstrate that knowledge base embedding models are generally effective for relation prediction but unable to give improvements for the state-of-art neural relation extraction model with the existing strategies, while pointing limitations of existing methods. |
| Tasks | Relation Extraction |
| Published | 2018-02-06 |
| URL | http://arxiv.org/abs/1802.02114v1 |
| http://arxiv.org/pdf/1802.02114v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigations-on-knowledge-base-embedding |
| Repo | |
| Framework | |
On Coresets for Logistic Regression
| Title | On Coresets for Logistic Regression |
| Authors | Alexander Munteanu, Chris Schwiegelshohn, Christian Sohler, David P. Woodruff |
| Abstract | Coresets are one of the central methods to facilitate the analysis of large data sets. We continue a recent line of research applying the theory of coresets to logistic regression. First, we show a negative result, namely, that no strongly sublinear sized coresets exist for logistic regression. To deal with intractable worst-case instances we introduce a complexity measure $\mu(X)$, which quantifies the hardness of compressing a data set for logistic regression. $\mu(X)$ has an intuitive statistical interpretation that may be of independent interest. For data sets with bounded $\mu(X)$-complexity, we show that a novel sensitivity sampling scheme produces the first provably sublinear $(1\pm\varepsilon)$-coreset. We illustrate the performance of our method by comparing to uniform sampling as well as to state of the art methods in the area. The experiments are conducted on real world benchmark data for logistic regression. |
| Tasks | |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08571v2 |
| http://arxiv.org/pdf/1805.08571v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-coresets-for-logistic-regression |
| Repo | |
| Framework | |
The role of grammar in transition-probabilities of subsequent words in English text
| Title | The role of grammar in transition-probabilities of subsequent words in English text |
| Authors | Rudolf Hanel, Stefan Thurner |
| Abstract | Sentence formation is a highly structured, history-dependent, and sample-space reducing (SSR) process. While the first word in a sentence can be chosen from the entire vocabulary, typically, the freedom of choosing subsequent words gets more and more constrained by grammar and context, as the sentence progresses. This sample-space reducing property offers a natural explanation of Zipf’s law in word frequencies, however, it fails to capture the structure of the word-to-word transition probability matrices of English text. Here we adopt the view that grammatical constraints (such as subject–predicate–object) locally re-order the word order in sentences that are sampled with a SSR word generation process. We demonstrate that superimposing grammatical structure – as a local word re-ordering (permutation) process – on a sample-space reducing process is sufficient to explain both, word frequencies and word-to-word transition probabilities. We compare the quality of the grammatically ordered SSR model in reproducing several test statistics of real texts with other text generation models, such as the Bernoulli model, the Simon model, and the Monkey typewriting model. |
| Tasks | Text Generation |
| Published | 2018-12-28 |
| URL | http://arxiv.org/abs/1812.10991v1 |
| http://arxiv.org/pdf/1812.10991v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-role-of-grammar-in-transition |
| Repo | |
| Framework | |
Deep Learning Object Detection Methods for Ecological Camera Trap Data
| Title | Deep Learning Object Detection Methods for Ecological Camera Trap Data |
| Authors | Stefan Schneider, Graham W. Taylor, Stefan C. Kremer |
| Abstract | Deep learning methods for computer vision tasks show promise for automating the data analysis of camera trap images. Ecological camera traps are a common approach for monitoring an ecosystem’s animal population, as they provide continual insight into an environment without being intrusive. However, the analysis of camera trap images is expensive, labour intensive, and time consuming. Recent advances in the field of deep learning for object detection show promise towards automating the analysis of camera trap images. Here, we demonstrate their capabilities by training and comparing two deep learning object detection classifiers, Faster R-CNN and YOLO v2.0, to identify, quantify, and localize animal species within camera trap images using the Reconyx Camera Trap and the self-labeled Gold Standard Snapshot Serengeti data sets. When trained on large labeled datasets, object recognition methods have shown success. We demonstrate their use, in the context of realistically sized ecological data sets, by testing if object detection methods are applicable for ecological research scenarios when utilizing transfer learning. Faster R-CNN outperformed YOLO v2.0 with average accuracies of 93.0% and 76.7% on the two data sets, respectively. Our findings show promising steps towards the automation of the labourious task of labeling camera trap images, which can be used to improve our understanding of the population dynamics of ecosystems across the planet. |
| Tasks | Object Detection, Object Recognition, Transfer Learning |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1803.10842v1 |
| http://arxiv.org/pdf/1803.10842v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-object-detection-methods-for |
| Repo | |
| Framework | |
Decision Variance in Online Learning
| Title | Decision Variance in Online Learning |
| Authors | Sattar Vakili, Alexis Boukouvalas, Qing Zhao |
| Abstract | Online learning has traditionally focused on the expected rewards. In this paper, a risk-averse online learning problem under the performance measure of the mean-variance of the rewards is studied. Both the bandit and full information settings are considered. The performance of several existing policies is analyzed, and new fundamental limitations on risk-averse learning is established. In particular, it is shown that although a logarithmic distribution-dependent regret in time $T$ is achievable (similar to the risk-neutral problem), the worst-case (i.e. minimax) regret is lower bounded by $\Omega(T)$ (in contrast to the $\Omega(\sqrt{T})$ lower bound in the risk-neutral problem). This sharp difference from the risk-neutral counterpart is caused by the the variance in the player’s decisions, which, while absent in the regret under the expected reward criterion, contributes to excess mean-variance due to the non-linearity of this risk measure. The role of the decision variance in regret performance reflects a risk-averse player’s desire for robust decisions and outcomes. |
| Tasks | |
| Published | 2018-07-24 |
| URL | http://arxiv.org/abs/1807.09089v2 |
| http://arxiv.org/pdf/1807.09089v2.pdf | |
| PWC | https://paperswithcode.com/paper/decision-variance-in-online-learning |
| Repo | |
| Framework | |
xGEMs: Generating Examplars to Explain Black-Box Models
| Title | xGEMs: Generating Examplars to Explain Black-Box Models |
| Authors | Shalmali Joshi, Oluwasanmi Koyejo, Been Kim, Joydeep Ghosh |
| Abstract | This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data points cross decision boundaries. To do so, we train an unsupervised implicit generative model – treated as a proxy to the data manifold. We summarize black-box model behavior quantitatively by perturbing data samples along the manifold. We demonstrate xGEMs’ ability to detect and quantify bias in model learning and also for understanding the changes in model behavior as training progresses. |
| Tasks | |
| Published | 2018-06-22 |
| URL | http://arxiv.org/abs/1806.08867v1 |
| http://arxiv.org/pdf/1806.08867v1.pdf | |
| PWC | https://paperswithcode.com/paper/xgems-generating-examplars-to-explain-black |
| Repo | |
| Framework | |
Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages
| Title | Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages |
| Authors | Shiyu Zhou, Shuang Xu, Bo Xu |
| Abstract | Sequence-to-sequence attention-based models integrate an acoustic, pronunciation and language model into a single neural network, which make them very suitable for multilingual automatic speech recognition (ASR). In this paper, we are concerned with multilingual speech recognition on low-resource languages by a single Transformer, one of sequence-to-sequence attention-based models. Sub-words are employed as the multilingual modeling unit without using any pronunciation lexicon. First, we show that a single multilingual ASR Transformer performs well on low-resource languages despite of some language confusion. We then look at incorporating language information into the model by inserting the language symbol at the beginning or at the end of the original sub-words sequence under the condition of language information being known during training. Experiments on CALLHOME datasets demonstrate that the multilingual ASR Transformer with the language symbol at the end performs better and can obtain relatively 10.5% average word error rate (WER) reduction compared to SHL-MLSTM with residual learning. We go on to show that, assuming the language information being known during training and testing, about relatively 12.4% average WER reduction can be observed compared to SHL-MLSTM with residual learning through giving the language symbol as the sentence start token. |
| Tasks | End-To-End Speech Recognition, Language Modelling, Speech Recognition |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.05059v2 |
| http://arxiv.org/pdf/1806.05059v2.pdf | |
| PWC | https://paperswithcode.com/paper/multilingual-end-to-end-speech-recognition |
| Repo | |
| Framework | |
Non-linear Canonical Correlation Analysis: A Compressed Representation Approach
| Title | Non-linear Canonical Correlation Analysis: A Compressed Representation Approach |
| Authors | Amichai Painsky, Meir Feder, Naftali Tishby |
| Abstract | Canonical Correlation Analysis (CCA) is a linear representation learning method that seeks maximally correlated variables in multi-view data. Non-linear CCA extends this notion to a broader family of transformations, which are more powerful in many real-world applications. Given the joint probability, the Alternating Conditional Expectation (ACE) algorithm provides an optimal solution to the non-linear CCA problem. However, it suffers from limited performance and an increasing computational burden when only a finite number of samples is available. In this work we introduce an information-theoretic compressed representation framework for the non-linear CCA problem (CRCCA), which extends the classical ACE approach. Our suggested framework seeks compact representations of the data that allow a maximal level of correlation. This way we control the trade-off between the flexibility and the complexity of the model. CRCCA provides theoretical bounds and optimality conditions, as we establish fundamental connections to rate-distortion theory, the information bottleneck and remote source coding. In addition, it allows a soft dimensionality reduction, as the compression level is determined by the mutual information between the original noisy data and the extracted signals. Finally, we introduce a simple implementation of the CRCCA framework, based on lattice quantization. |
| Tasks | Dimensionality Reduction, Quantization, Representation Learning |
| Published | 2018-10-31 |
| URL | https://arxiv.org/abs/1810.13259v2 |
| https://arxiv.org/pdf/1810.13259v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-information-theoretic-framework-for-non |
| Repo | |
| Framework | |
A plug-in approach to maximising precision at the top and recall at the top
| Title | A plug-in approach to maximising precision at the top and recall at the top |
| Authors | Dirk Tasche |
| Abstract | For information retrieval and binary classification, we show that precision at the top (or precision at k) and recall at the top (or recall at k) are maximised by thresholding the posterior probability of the positive class. This finding is a consequence of a result on constrained minimisation of the cost-sensitive expected classification error which generalises an earlier related result from the literature. |
| Tasks | Information Retrieval |
| Published | 2018-04-09 |
| URL | http://arxiv.org/abs/1804.03077v1 |
| http://arxiv.org/pdf/1804.03077v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-plug-in-approach-to-maximising-precision-at |
| Repo | |
| Framework | |
Enhancing Chinese Intent Classification by Dynamically Integrating Character Features into Word Embeddings with Ensemble Techniques
| Title | Enhancing Chinese Intent Classification by Dynamically Integrating Character Features into Word Embeddings with Ensemble Techniques |
| Authors | Ruixi Lin, Charles Costello, Charles Jankowski |
| Abstract | Intent classification has been widely researched on English data with deep learning approaches that are based on neural networks and word embeddings. The challenge for Chinese intent classification stems from the fact that, unlike English where most words are made up of 26 phonologic alphabet letters, Chinese is logographic, where a Chinese character is a more basic semantic unit that can be informative and its meaning does not vary too much in contexts. Chinese word embeddings alone can be inadequate for representing words, and pre-trained embeddings can suffer from not aligning well with the task at hand. To account for the inadequacy and leverage Chinese character information, we propose a low-effort and generic way to dynamically integrate character embedding based feature maps with word embedding based inputs, whose resulting word-character embeddings are stacked with a contextual information extraction module to further incorporate context information for predictions. On top of the proposed model, we employ an ensemble method to combine single models and obtain the final result. The approach is data-independent without relying on external sources like pre-trained word embeddings. The proposed model outperforms baseline models and existing methods. |
| Tasks | Intent Classification, Word Embeddings |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.08914v1 |
| http://arxiv.org/pdf/1805.08914v1.pdf | |
| PWC | https://paperswithcode.com/paper/enhancing-chinese-intent-classification-by |
| Repo | |
| Framework | |
Individual Fairness in Hindsight
| Title | Individual Fairness in Hindsight |
| Authors | Swati Gupta, Vijay Kamble |
| Abstract | Since many critical decisions impacting human lives are increasingly being made by algorithms, it is important to ensure that the treatment of individuals under such algorithms is demonstrably fair under reasonable notions of fairness. One compelling notion proposed in the literature is that of individual fairness (IF), which advocates that similar individuals should be treated similarly (Dwork et al. 2012). Originally proposed for offline decisions, this notion does not, however, account for temporal considerations relevant for online decision-making. In this paper, we extend the notion of IF to account for the time at which a decision is made, in settings where there exists a notion of conduciveness of decisions as perceived by the affected individuals. We introduce two definitions: (i) fairness-across-time (FT) and (ii) fairness-in-hindsight (FH). FT is the simplest temporal extension of IF where treatment of individuals is required to be individually fair relative to the past as well as future, while in FH, we require a one-sided notion of individual fairness that is defined relative to only the past decisions. We show that these two definitions can have drastically different implications in the setting where the principal needs to learn the utility model. Linear regret relative to optimal individually fair decisions is inevitable under FT for non-trivial examples. On the other hand, we design a new algorithm: Cautious Fair Exploration (CaFE), which satisfies FH and achieves sub-linear regret guarantees for a broad range of settings. We characterize lower bounds showing that these guarantees are order-optimal in the worst case. FH can thus be embedded as a primary safeguard against unfair discrimination in algorithmic deployments, without hindering the ability to take good decisions in the long-run. |
| Tasks | Decision Making |
| Published | 2018-12-10 |
| URL | http://arxiv.org/abs/1812.04069v3 |
| http://arxiv.org/pdf/1812.04069v3.pdf | |
| PWC | https://paperswithcode.com/paper/individual-fairness-in-hindsight |
| Repo | |
| Framework | |
CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision
| Title | CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision |
| Authors | Navaneet K L, Priyanka Mandikal, Mayank Agarwal, R. Venkatesh Babu |
| Abstract | Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for data-driven approaches in learning such properties. We consider the task of single image 3D point cloud reconstruction, and aim to utilize multiple foreground masks as our supervisory data to alleviate the need for large scale 3D datasets. A novel differentiable projection module, called ‘CAPNet’, is introduced to obtain such 2D masks from a predicted 3D point cloud. The key idea is to model the projections as a continuous approximation of the points in the point cloud. To overcome the challenges of sparse projection maps, we propose a loss formulation termed ‘affinity loss’ to generate outlier-free reconstructions. We significantly outperform the existing projection based approaches on a large-scale synthetic dataset. We show the utility and generalizability of such a 2D supervised approach through experiments on a real-world dataset, where lack of 3D data can be a serious concern. To further enhance the reconstructions, we also propose a test stage optimization procedure to obtain reconstructions that display high correspondence with the observed input image. |
| Tasks | |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11731v1 |
| http://arxiv.org/pdf/1811.11731v1.pdf | |
| PWC | https://paperswithcode.com/paper/capnet-continuous-approximation-projection |
| Repo | |
| Framework | |
