Paper Group ANR 576
WebProtégé: A Cloud-Based Ontology Editor. To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions. Towards Global Remote Discharge Estimation: Using the Few to Estimate The Many. Flexible Auto-weighted Local-coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering. A Light …
WebProtégé: A Cloud-Based Ontology Editor
| Title | WebProtégé: A Cloud-Based Ontology Editor |
| Authors | Matthew Horridge, Rafael S. Gonçalves, Csongor I. Nyulas, Tania Tudorache, Mark A. Musen |
| Abstract | We present WebProt'eg'e, a tool to develop ontologies represented in the Web Ontology Language (OWL). WebProt'eg'e is a cloud-based application that allows users to collaboratively edit OWL ontologies, and it is available for use at https://webprotege.stanford.edu. WebProt'ege'e currently hosts more than 68,000 OWL ontology projects and has over 50,000 user accounts. In this paper, we detail the main new features of the latest version of WebProt'eg'e. |
| Tasks | |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.08251v2 |
| http://arxiv.org/pdf/1902.08251v2.pdf | |
| PWC | https://paperswithcode.com/paper/webprotege-a-cloud-based-ontology-editor |
| Repo | |
| Framework | |
To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions
| Title | To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions |
| Authors | Rolf Jagerman, Harrie Oosterhuis, Maarten de Rijke |
| Abstract | Learning to Rank (LTR) from user interactions is challenging as user feedback often contains high levels of bias and noise. At the moment, two methodologies for dealing with bias prevail in the field of LTR: counterfactual methods that learn from historical data and model user behavior to deal with biases; and online methods that perform interventions to deal with bias but use no explicit user models. For practitioners the decision between either methodology is very important because of its direct impact on end users. Nevertheless, there has never been a direct comparison between these two approaches to unbiased LTR. In this study we provide the first benchmarking of both counterfactual and online LTR methods under different experimental conditions. Our results show that the choice between the methodologies is consequential and depends on the presence of selection bias, and the degree of position bias and interaction noise. In settings with little bias or noise counterfactual methods can obtain the highest ranking performance; however, in other circumstances their optimization can be detrimental to the user experience. Conversely, online methods are very robust to bias and noise but require control over the displayed rankings. Our findings confirm and contradict existing expectations on the impact of model-based and intervention-based methods in LTR, and allow practitioners to make an informed decision between the two methodologies. |
| Tasks | Learning-To-Rank |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.06412v1 |
| https://arxiv.org/pdf/1907.06412v1.pdf | |
| PWC | https://paperswithcode.com/paper/to-model-or-to-intervene-a-comparison-of |
| Repo | |
| Framework | |
Towards Global Remote Discharge Estimation: Using the Few to Estimate The Many
| Title | Towards Global Remote Discharge Estimation: Using the Few to Estimate The Many |
| Authors | Yotam Gigi, Gal Elidan, Avinatan Hassidim, Yossi Matias, Zach Moshe, Sella Nevo, Guy Shalev, Ami Wiesel |
| Abstract | Learning hydrologic models for accurate riverine flood prediction at scale is a challenge of great importance. One of the key difficulties is the need to rely on in-situ river discharge measurements, which can be quite scarce and unreliable, particularly in regions where floods cause the most damage every year. Accordingly, in this work we tackle the problem of river discharge estimation at different river locations. A core characteristic of the data at hand (e.g. satellite measurements) is that we have few measurements for many locations, all sharing the same physics that underlie the water discharge. We capture this scenario in a simple but powerful common mechanism regression (CMR) model with a local component as well as a shared one which captures the global discharge mechanism. The resulting learning objective is non-convex, but we show that we can find its global optimum by leveraging the power of joining local measurements across sites. In particular, using a spectral initialization with provable near-optimal accuracy, we can find the optimum using standard descent methods. We demonstrate the efficacy of our approach for the problem of discharge estimation using simulations. |
| Tasks | |
| Published | 2019-01-03 |
| URL | http://arxiv.org/abs/1901.00786v1 |
| http://arxiv.org/pdf/1901.00786v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-global-remote-discharge-estimation |
| Repo | |
| Framework | |
Flexible Auto-weighted Local-coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering
| Title | Flexible Auto-weighted Local-coordinate Concept Factorization: A Robust Framework for Unsupervised Clustering |
| Authors | Zhao Zhang, Yan Zhang, Sheng Li, Guangcan Liu, Dan Zeng, Shuicheng Yan, Meng Wang |
| Abstract | Concept Factorization (CF) and its variants may produce inaccurate representation and clustering results due to the sensitivity to noise, hard constraint on the reconstruction error and pre-obtained approximate similarities. To improve the representation ability, a novel unsupervised Robust Flexible Auto-weighted Local-coordinate Concept Factorization (RFA-LCF) framework is proposed for clustering high-dimensional data. Specifically, RFA-LCF integrates the robust flexible CF by clean data space recovery, robust sparse local-coordinate coding and adaptive weighting into a unified model. RFA-LCF improves the representations by enhancing the robustness of CF to noise and errors, providing a flexible constraint on the reconstruction error and optimizing the locality jointly. For robust learning, RFA-LCF clearly learns a sparse projection to recover the underlying clean data space, and then the flexible CF is performed in the projected feature space. RFA-LCF also uses a L2,1-norm based flexible residue to encode the mismatch between the recovered data and its reconstruction, and uses the robust sparse local-coordinate coding to represent data using a few nearby basis concepts. For auto-weighting, RFA-LCF jointly preserves the manifold structures in the basis concept space and new coordinate space in an adaptive manner by minimizing the reconstruction errors on clean data, anchor points and coordinates. By updating the local-coordinate preserving data, basis concepts and new coordinates alternately, the representation abilities can be potentially improved. Extensive results on public databases show that RFA-LCF delivers the state-of-the-art clustering results compared with other related methods. |
| Tasks | |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00523v1 |
| https://arxiv.org/pdf/1909.00523v1.pdf | |
| PWC | https://paperswithcode.com/paper/flexible-auto-weighted-local-coordinate |
| Repo | |
| Framework | |
A Lightweight Recurrent Network for Sequence Modeling
| Title | A Lightweight Recurrent Network for Sequence Modeling |
| Authors | Biao Zhang, Rico Sennrich |
| Abstract | Recurrent networks have achieved great success on various sequential tasks with the assistance of complex recurrent units, but suffer from severe computational inefficiency due to weak parallelization. One direction to alleviate this issue is to shift heavy computations outside the recurrence. In this paper, we propose a lightweight recurrent network, or LRN. LRN uses input and forget gates to handle long-range dependencies as well as gradient vanishing and explosion, with all parameter related calculations factored outside the recurrence. The recurrence in LRN only manipulates the weight assigned to each token, tightly connecting LRN with self-attention networks. We apply LRN as a drop-in replacement of existing recurrent units in several neural sequential models. Extensive experiments on six NLP tasks show that LRN yields the best running efficiency with little or no loss in model performance. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13324v1 |
| https://arxiv.org/pdf/1905.13324v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-lightweight-recurrent-network-for-sequence |
| Repo | |
| Framework | |
Fixed Pattern Noise Reduction for Infrared Images Based on Cascade Residual Attention CNN
| Title | Fixed Pattern Noise Reduction for Infrared Images Based on Cascade Residual Attention CNN |
| Authors | Juntao Guan, Rui Lai, Ai Xiong, Zesheng Liu, Lin Gu |
| Abstract | Existing fixed pattern noise reduction (FPNR) methods are easily affected by the motion state of the scene and working condition of the image sensor, which leads to over smooth effects, ghosting artifacts as well as slow convergence rate. To address these issues, we design an innovative cascade convolution neural network (CNN) model with residual skip connections to realize single frame blind FPNR operation without any parameter tuning. Moreover, a coarse-fine convolution (CF-Conv) unit is introduced to extract complementary features in various scales and fuse them to pick more spatial information. Inspired by the success of the visual attention mechanism, we further propose a particular spatial-channel noise attention unit (SCNAU) to separate the scene details from fixed pattern noise more thoroughly and recover the real scene more accurately. Experimental results on test data demonstrate that the proposed cascade CNN-FPNR method outperforms the existing FPNR methods in both of visual effect and quantitative assessment. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09858v1 |
| https://arxiv.org/pdf/1910.09858v1.pdf | |
| PWC | https://paperswithcode.com/paper/fixed-pattern-noise-reduction-for-infrared |
| Repo | |
| Framework | |
Practical User Feedback-driven Internal Search Using Online Learning to Rank
| Title | Practical User Feedback-driven Internal Search Using Online Learning to Rank |
| Authors | Rajhans Samdani, Pierre Rappolt, Ankit Goyal, Pratyus Patnaik |
| Abstract | We present a system, Spoke, for creating and searching internal knowledge base (KB) articles for organizations. Spoke is available as a SaaS (Software-as-a-Service) product deployed across hundreds of organizations with a diverse set of domains. Spoke continually improves search quality using conversational user feedback which allows it to provide better search experience than standard information retrieval systems without encoding any explicit domain knowledge. We achieve this by using a real-time online learning-to-rank (L2R) algorithm that automatically customizes relevance scoring for each organization deploying Spoke by using a query similarity kernel. The focus of this paper is on incorporating practical considerations into our relevance scoring function and algorithm that make Spoke easy to deploy and suitable for handling events that naturally happen over the life-cycle of any KB deployment. We show that Spoke outperforms competitive baselines by up to 41% in offline F1 comparisons. |
| Tasks | Information Retrieval, Learning-To-Rank |
| Published | 2019-06-15 |
| URL | https://arxiv.org/abs/1906.06581v2 |
| https://arxiv.org/pdf/1906.06581v2.pdf | |
| PWC | https://paperswithcode.com/paper/practical-user-feedback-driven-internal |
| Repo | |
| Framework | |
DeepObfusCode: Source Code Obfuscation Through Sequence-to-Sequence Networks
| Title | DeepObfusCode: Source Code Obfuscation Through Sequence-to-Sequence Networks |
| Authors | Siddhartha Datta |
| Abstract | The paper explores a novel methodology in source code obfuscation through the application of text-based recurrent neural network (RNN) encoder-decoder models in ciphertext generation and key generation. Sequence-to-sequence models are incorporated into the model architecture to generate obfuscated code, generate the deobfuscation key, and live execution. Quantitative benchmark comparison to existing obfuscation methods indicate significant improvement in stealth and execution cost for the proposed solution, and experiments regarding the model’s properties yield positive results regarding its character variation, dissimilarity to the original codebase, and consistent length of obfuscated code. |
| Tasks | |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.01837v2 |
| https://arxiv.org/pdf/1909.01837v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepobfuscode-source-code-obfuscation-through |
| Repo | |
| Framework | |
Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
| Title | Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation |
| Authors | Kuan Fang, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei |
| Abstract | The fundamental challenge of planning for multi-step manipulation is to find effective and plausible action sequences that lead to the task goal. We present Cascaded Variational Inference (CAVIN) Planner, a model-based method that hierarchically generates plans by sampling from latent spaces. To facilitate planning over long time horizons, our method learns latent representations that decouple the prediction of high-level effects from the generation of low-level motions through cascaded variational inference. This enables us to model dynamics at two different levels of temporal resolutions for hierarchical planning. We evaluate our approach in three multi-step robotic manipulation tasks in cluttered tabletop environments given high-dimensional observations. Empirical results demonstrate that the proposed method outperforms state-of-the-art model-based methods by strategically interacting with multiple objects. |
| Tasks | |
| Published | 2019-10-29 |
| URL | https://arxiv.org/abs/1910.13395v2 |
| https://arxiv.org/pdf/1910.13395v2.pdf | |
| PWC | https://paperswithcode.com/paper/191013395 |
| Repo | |
| Framework | |
Variance Reduction in Gradient Exploration for Online Learning to Rank
| Title | Variance Reduction in Gradient Exploration for Online Learning to Rank |
| Authors | Huazheng Wang, Sonwoo Kim, Eric McCord-Snook, Qingyun Wu, Hongning Wang |
| Abstract | Online Learning to Rank (OL2R) algorithms learn from implicit user feedback on the fly. The key of such algorithms is an unbiased estimation of gradients, which is often (trivially) achieved by uniformly sampling from the entire parameter space. This unfortunately introduces high-variance in gradient estimation, and leads to a worse regret of model estimation, especially when the dimension of parameter space is large. In this paper, we aim at reducing the variance of gradient estimation in OL2R algorithms. We project the selected updating direction into a space spanned by the feature vectors from examined documents under the current query (termed the “document space” for short), after interleaved test. Our key insight is that the result of interleaved test solely is governed by a user’s relevance evaluation over the examined documents. Hence, the true gradient introduced by this test result should lie in the constructed document space, and components orthogonal to the document space in the proposed gradient can be safely removed for variance reduction. We prove that the projected gradient is an unbiased estimation of the true gradient, and show that this lower-variance gradient estimation results in significant regret reduction. Our proposed method is compatible with all existing OL2R algorithms which rank documents using a linear model. Extensive experimental comparisons with several state-of-the-art OL2R algorithms have confirmed the effectiveness of our proposed method in reducing the variance of gradient estimation and improving overall performance. |
| Tasks | Learning-To-Rank |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03766v3 |
| https://arxiv.org/pdf/1906.03766v3.pdf | |
| PWC | https://paperswithcode.com/paper/variance-reduction-in-gradient-exploration |
| Repo | |
| Framework | |
Learning Domain Randomization Distributions for Training Robust Locomotion Policies
| Title | Learning Domain Randomization Distributions for Training Robust Locomotion Policies |
| Authors | Melissa Mozifian, Juan Camilo Gamboa Higuera, David Meger, Gregory Dudek |
| Abstract | Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of success stories typically use real world data in order to carefully select the DR distribution, or incorporate real world trajectories to better estimate appropriate randomization distributions. In this paper, we consider the problem of finding good domain randomization parameters for simulation, without prior access to data from the target system. We explore the use of gradient-based search methods to learn a domain randomization with the following properties: 1) The trained policy should be successful in environments sampled from the domain randomization distribution 2) The domain randomization distribution should be wide enough so that the experience similar to the target robot system is observed during training, while addressing the practicality of training finite capacity models. These two properties aim to ensure the trajectories encountered in the target system are close to those observed during training, as existing methods in machine learning are better suited for interpolation than extrapolation. We show how adapting the domain randomization distribution while training context-conditioned policies results in improvements on jump-start and asymptotic performance when transferring a learned policy to the target environment. |
| Tasks | |
| Published | 2019-06-02 |
| URL | https://arxiv.org/abs/1906.00410v2 |
| https://arxiv.org/pdf/1906.00410v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600410 |
| Repo | |
| Framework | |
On the Sensitivity of Adversarial Robustness to Input Data Distributions
| Title | On the Sensitivity of Adversarial Robustness to Input Data Distributions |
| Authors | Gavin Weiguang Ding, Kry Yik Chau Lui, Xiaomeng Jin, Luyu Wang, Ruitong Huang |
| Abstract | Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the most popular robust training method in the literature, adversarial training: Adversarial robustness, unlike clean accuracy, is sensitive to the input data distribution. Even a semantics-preserving transformations on the input data distribution can cause a significantly different robustness for the adversarial trained model that is both trained and evaluated on the new distribution. Our discovery of such sensitivity on data distribution is based on a study which disentangles the behaviors of clean accuracy and robust accuracy of the Bayes classifier. Empirical investigations further confirm our finding. We construct semantically-identical variants for MNIST and CIFAR10 respectively, and show that standardly trained models achieve comparable clean accuracies on them, but adversarially trained models achieve significantly different robustness accuracies. This counter-intuitive phenomenon indicates that input data distribution alone can affect the adversarial robustness of trained neural networks, not necessarily the tasks themselves. Lastly, we discuss the practical implications on evaluating adversarial robustness, and make initial attempts to understand this complex phenomenon. |
| Tasks | |
| Published | 2019-02-22 |
| URL | http://arxiv.org/abs/1902.08336v1 |
| http://arxiv.org/pdf/1902.08336v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-sensitivity-of-adversarial-robustness |
| Repo | |
| Framework | |
Application of Word2vec in Phoneme Recognition
| Title | Application of Word2vec in Phoneme Recognition |
| Authors | Xin Feng, Lei Wang |
| Abstract | In this paper, we present how to hybridize a Word2vec model and an attention-based end-to-end speech recognition model. We build a phoneme recognition system based on Listen, Attend and Spell model. And the phoneme recognition model uses a word2vec model to initialize the embedding matrix for the improvement of the performance, which can increase the distance among the phoneme vectors. At the same time, in order to solve the problem of overfitting in the 61 phoneme recognition model on TIMIT dataset, we propose a new training method. A 61-39 phoneme mapping comparison table is used to inverse map the phonemes of the dataset to generate more 61 phoneme training data. At the end of training, replace the dataset with a standard dataset for corrective training. Our model can achieve the best result under the TIMIT dataset which is 16.5% PER (Phoneme Error Rate). |
| Tasks | End-To-End Speech Recognition, Speech Recognition |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08011v2 |
| https://arxiv.org/pdf/1912.08011v2.pdf | |
| PWC | https://paperswithcode.com/paper/application-of-word2vec-in-phoneme |
| Repo | |
| Framework | |
Pixel-wise Regression: 3D Hand Pose Estimation via Spatial-form Representation and Differentiable Decoder
| Title | Pixel-wise Regression: 3D Hand Pose Estimation via Spatial-form Representation and Differentiable Decoder |
| Authors | Xingyuan Zhang, Fuhai Zhang |
| Abstract | 3D Hand pose estimation from a single depth image is an essential topic in computer vision and human-computer interaction. Although the rising of deep learning method boosts the accuracy a lot, the problem is still hard to solve due to the complex structure of the human hand. Existing methods with deep learning either lose spatial information of hand structure or lack a direct supervision of joint coordinates. In this paper, we propose a novel Pixel-wise Regression method, which use spatial-form representation (SFR) and differentiable decoder (DD) to solve the two problems. To use our method, we build a model, in which we design a particular SFR and its correlative DD which divided the 3D joint coordinates into two parts, plane coordinates and depth coordinates and use two modules named Plane Regression (PR) and Depth Regression (DR) to deal with them respectively. We conduct an ablation experiment to show the method we proposed achieve better results than the former methods. We also make an exploration on how different training strategies influence the learned SFRs and results. The experiment on three public datasets demonstrates that our model is comparable with the existing state-of-the-art models and in one of them our model can reduce mean 3D joint error by 25%. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02085v2 |
| https://arxiv.org/pdf/1905.02085v2.pdf | |
| PWC | https://paperswithcode.com/paper/pixel-wise-regression-3d-hand-pose-estimation |
| Repo | |
| Framework | |
Discovering Heterogeneous Subsequences for Trajectory Classification
| Title | Discovering Heterogeneous Subsequences for Trajectory Classification |
| Authors | Carlos Andres Ferrero, Lucas May Petry, Luis Otavio Alvares, Willian Zalewski, Vania Bogorny |
| Abstract | In this paper we propose a new parameter-free method for trajectory classification which finds the best trajectory partition and dimension combination for robust trajectory classification. Preliminary experiments show that our approach is very promising. |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07722v1 |
| http://arxiv.org/pdf/1903.07722v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-heterogeneous-subsequences-for |
| Repo | |
| Framework | |
