Paper Group ANR 798
Reasoning over RDF Knowledge Bases using Deep Learning. Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages. A Global Information Based Adaptive Threshold for Grouping Large Scale Global Optimization Problems. Neural Inverse Rendering for General Reflectance Photometric Stereo. DropPruning for Model Compression. Personality f …
Reasoning over RDF Knowledge Bases using Deep Learning
| Title | Reasoning over RDF Knowledge Bases using Deep Learning |
| Authors | Monireh Ebrahimi, Md Kamruzzaman Sarker, Federico Bianchi, Ning Xie, Derek Doran, Pascal Hitzler |
| Abstract | Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field. Reasoning, i.e., the drawing of logical inferences from knowledge expressed in such standards, is traditionally based on logical deductive methods and algorithms which can be proven to be sound and complete and terminating, i.e. correct in a very strong sense. For various reasons, though, in particular, the scalability issues arising from the ever-increasing amounts of Semantic Web data available and the inability of deductive algorithms to deal with noise in the data, it has been argued that alternative means of reasoning should be investigated which bear high promise for high scalability and better robustness. From this perspective, deductive algorithms can be considered the gold standard regarding correctness against which alternative methods need to be tested. In this paper, we show that it is possible to train a Deep Learning system on RDF knowledge graphs, such that it is able to perform reasoning over new RDF knowledge graphs, with high precision and recall compared to the deductive gold standard. |
| Tasks | Knowledge Graphs |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.04132v1 |
| http://arxiv.org/pdf/1811.04132v1.pdf | |
| PWC | https://paperswithcode.com/paper/reasoning-over-rdf-knowledge-bases-using-deep |
| Repo | |
| Framework | |
Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages
| Title | Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages |
| Authors | Enno Hermann, Herman Kamper, Sharon Goldwater |
| Abstract | Unsupervised subword modeling aims to learn low-level representations of speech audio in “zero-resource” settings: that is, without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good representation should capture phonetic content and abstract away from other types of variability, such as speaker differences and channel noise. Previous work in this area has primarily focused on learning from target language data only, and has been evaluated only intrinsically. Here we directly compare multiple methods, including some that use only target language speech data and some that use transcribed speech from other (non-target) languages, and we evaluate using two intrinsic measures as well as on a downstream unsupervised word segmentation and clustering task. We find that combining two existing target-language-only methods yields better features than either method alone. Nevertheless, even better results are obtained by extracting target language bottleneck features using a model trained on other languages. Cross-lingual training using just one other language is enough to provide this benefit, but multilingual training helps even more. In addition to these results, which hold across both intrinsic measures and the extrinsic task, we discuss the qualitative differences between the different types of learned features. |
| Tasks | |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.04791v1 |
| http://arxiv.org/pdf/1811.04791v1.pdf | |
| PWC | https://paperswithcode.com/paper/multilingual-and-unsupervised-subword |
| Repo | |
| Framework | |
A Global Information Based Adaptive Threshold for Grouping Large Scale Global Optimization Problems
| Title | A Global Information Based Adaptive Threshold for Grouping Large Scale Global Optimization Problems |
| Authors | An Chen, Yipeng Zhang, Zhigang Ren, Yongsheng Liang, Bei Pang |
| Abstract | By taking the idea of divide-and-conquer, cooperative coevolution (CC) provides a powerful architecture for large scale global optimization (LSGO) problems, but its efficiency relies highly on the decomposition strategy. It has been shown that differential grouping (DG) performs well on decomposing LSGO problems by effectively detecting the interaction among decision variables. However, its decomposition accuracy depends highly on the threshold. To improve the decomposition accuracy of DG, a global information based adaptive threshold setting algorithm (GIAT) is proposed in this paper. On the one hand, by reducing the sensitivity of the indicator in DG to the roundoff error and the magnitude of contribution weight of subcomponent, we proposed a new indicator for two variables which is much more sensitive to their interaction. On the other hand, instead of setting the threshold only based on one pair of variables, the threshold is generated from the interaction information for all pair of variables. By conducting the experiments on two sets of LSGO benchmark functions, the correctness and robustness of this new indicator and GIAT were verified. |
| Tasks | |
| Published | 2018-03-01 |
| URL | http://arxiv.org/abs/1803.00152v1 |
| http://arxiv.org/pdf/1803.00152v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-global-information-based-adaptive-threshold |
| Repo | |
| Framework | |
Neural Inverse Rendering for General Reflectance Photometric Stereo
| Title | Neural Inverse Rendering for General Reflectance Photometric Stereo |
| Authors | Tatsunori Taniai, Takanori Maehara |
| Abstract | We present a novel convolutional neural network architecture for photometric stereo (Woodham, 1980), a problem of recovering 3D object surface normals from multiple images observed under varying illuminations. Despite its long history in computer vision, the problem still shows fundamental challenges for surfaces with unknown general reflectance properties (BRDFs). Leveraging deep neural networks to learn complicated reflectance models is promising, but studies in this direction are very limited due to difficulties in acquiring accurate ground truth for training and also in designing networks invariant to permutation of input images. In order to address these challenges, we propose a physics based unsupervised learning framework where surface normals and BRDFs are predicted by the network and fed into the rendering equation to synthesize observed images. The network weights are optimized during testing by minimizing reconstruction loss between observed and synthesized images. Thus, our learning process does not require ground truth normals or even pre-training on external images. Our method is shown to achieve the state-of-the-art performance on a challenging real-world scene benchmark. |
| Tasks | |
| Published | 2018-02-28 |
| URL | http://arxiv.org/abs/1802.10328v2 |
| http://arxiv.org/pdf/1802.10328v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-inverse-rendering-for-general |
| Repo | |
| Framework | |
DropPruning for Model Compression
| Title | DropPruning for Model Compression |
| Authors | Haipeng Jia, Xueshuang Xiang, Da Fan, Meiyu Huang, Changhao Sun, Qingliang Meng, Yang He, Chen Chen |
| Abstract | Deep neural networks (DNNs) have dramatically achieved great success on a variety of challenging tasks. However, most of the successful DNNs are structurally so complex, leading to much storage requirement and floating-point operation. This paper proposes a novel technique, named Drop Pruning, to compress the DNNs by pruning the weights from a dense high-accuracy baseline model without accuracy loss. Drop Pruning also falls into the standard iterative prune-retrain procedure, where a \emph{drop} strategy exists at each pruning step: \emph{drop out}, stochastic deleting some unimportant weights and \emph{drop in}, stochastic recovering some pruned weights. \emph{Drop out} and \emph{drop in} are supposed to handle the two drawbacks of the traditional pruning methods: local importance judgment and irretrievable pruning process, respectively. The suitable choosing of \emph{drop} probabilities can decrease the model size during pruning process and lead it to flow to the target sparsity. Drop Pruning also has some similar spirits with dropout, a stochastic algorithm in Integer Optimization and the Dense-Sparse-Dense training technique. Drop Pruning can significantly reducing overfitting while compressing the model. Experimental results demonstrates that Drop Pruning can achieve the state-of-the-art performance on many benchmark pruning tasks, about ${11.1\times}$ compression of VGG-16 on CIFAR10 and ${14.3\times}$ compression of LeNet-5 on MNIST without accuracy loss, which may provide some new insights into the aspect of model compression. |
| Tasks | Model Compression |
| Published | 2018-12-05 |
| URL | http://arxiv.org/abs/1812.02035v1 |
| http://arxiv.org/pdf/1812.02035v1.pdf | |
| PWC | https://paperswithcode.com/paper/droppruning-for-model-compression |
| Repo | |
| Framework | |
Personality facets recognition from text
| Title | Personality facets recognition from text |
| Authors | Wesley Ramos dos Santos, Ivandre Paraboni |
| Abstract | Fundamental Big Five personality traits (e.g., Extraversion) and their facets (e.g., Activity) are known to correlate with a broad range of linguistic features and, accordingly, the recognition of personality traits from text is a well-known Natural Language Processing task. Labelling text data with facets information, however, may require the use of lengthy personality inventories, and perhaps for that reason existing computational models of this kind are usually limited to the recognition of the fundamental traits. Based on these observations, this paper investigates the issue of personality facets recognition from text labelled only with information available from a shorter personality inventory. In doing so, we provide a low-cost model for the recognition of certain personality facets, and present reference results for further studies in this field. |
| Tasks | |
| Published | 2018-10-06 |
| URL | http://arxiv.org/abs/1810.02980v2 |
| http://arxiv.org/pdf/1810.02980v2.pdf | |
| PWC | https://paperswithcode.com/paper/personality-facets-recognition-from-text |
| Repo | |
| Framework | |
A New Variational Model for Binary Classification in the Supervised Learning Context
| Title | A New Variational Model for Binary Classification in the Supervised Learning Context |
| Authors | Carlos David Brito Pacheco, Carlos Francisco Brito Loeza |
| Abstract | We examine the supervised learning problem in its continuous setting and give a general optimality condition through techniques of functional analysis and the calculus of variations. This enables us to solve the optimality condition for the desired function u numerically and make several comparisons with other widely utilized supervised learning models. We employ the accuracy and area under the receiver operating characteristic curve as metrics of the performance. Finally, 3 analyses are conducted based on these two mentioned metrics where we compare the models and make conclusions to determine whether or not our method is competitive. |
| Tasks | |
| Published | 2018-07-10 |
| URL | http://arxiv.org/abs/1807.03431v2 |
| http://arxiv.org/pdf/1807.03431v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-variational-model-for-binary |
| Repo | |
| Framework | |
Robust Fitting in Computer Vision: Easy or Hard?
| Title | Robust Fitting in Computer Vision: Easy or Hard? |
| Authors | Tat-Jun Chin, Zhipeng Cai, Frank Neumann |
| Abstract | Robust model fitting plays a vital role in computer vision, and research into algorithms for robust fitting continues to be active. Arguably the most popular paradigm for robust fitting in computer vision is consensus maximisation, which strives to find the model parameters that maximise the number of inliers. Despite the significant developments in algorithms for consensus maximisation, there has been a lack of fundamental analysis of the problem in the computer vision literature. In particular, whether consensus maximisation is “tractable” remains a question that has not been rigorously dealt with, thus making it difficult to assess and compare the performance of proposed algorithms, relative to what is theoretically achievable. To shed light on these issues, we present several computational hardness results for consensus maximisation. Our results underline the fundamental intractability of the problem, and resolve several ambiguities existing in the literature. |
| Tasks | |
| Published | 2018-02-18 |
| URL | http://arxiv.org/abs/1802.06464v3 |
| http://arxiv.org/pdf/1802.06464v3.pdf | |
| PWC | https://paperswithcode.com/paper/robust-fitting-in-computer-vision-easy-or |
| Repo | |
| Framework | |
Depth-Limited Solving for Imperfect-Information Games
| Title | Depth-Limited Solving for Imperfect-Information Games |
| Authors | Noam Brown, Tuomas Sandholm, Brandon Amos |
| Abstract | A fundamental challenge in imperfect-information games is that states do not have well-defined values. As a result, depth-limited search algorithms used in single-agent settings and perfect-information games do not apply. This paper introduces a principled way to conduct depth-limited solving in imperfect-information games by allowing the opponent to choose among a number of strategies for the remainder of the game at the depth limit. Each one of these strategies results in a different set of values for leaf nodes. This forces an agent to be robust to the different strategies an opponent may employ. We demonstrate the effectiveness of this approach by building a master-level heads-up no-limit Texas hold’em poker AI that defeats two prior top agents using only a 4-core CPU and 16 GB of memory. Developing such a powerful agent would have previously required a supercomputer. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.08195v1 |
| http://arxiv.org/pdf/1805.08195v1.pdf | |
| PWC | https://paperswithcode.com/paper/depth-limited-solving-for-imperfect |
| Repo | |
| Framework | |
Adversarial quantum circuit learning for pure state approximation
| Title | Adversarial quantum circuit learning for pure state approximation |
| Authors | Marcello Benedetti, Edward Grant, Leonard Wossnig, Simone Severini |
| Abstract | Adversarial learning is one of the most successful approaches to modelling high-dimensional probability distributions from data. The quantum computing community has recently begun to generalize this idea and to look for potential applications. In this work, we derive an adversarial algorithm for the problem of approximating an unknown quantum pure state. Although this could be done on universal quantum computers, the adversarial formulation enables us to execute the algorithm on near-term quantum computers. Two parametrized circuits are optimized in tandem: One tries to approximate the target state, the other tries to distinguish between target and approximated state. Supported by numerical simulations, we show that resilient backpropagation algorithms perform remarkably well in optimizing the two circuits. We use the bipartite entanglement entropy to design an efficient heuristic for the stopping criterion. Our approach may find application in quantum state tomography. |
| Tasks | Quantum State Tomography |
| Published | 2018-06-01 |
| URL | http://arxiv.org/abs/1806.00463v3 |
| http://arxiv.org/pdf/1806.00463v3.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-quantum-circuit-learning-for-pure |
| Repo | |
| Framework | |
Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration
| Title | Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration |
| Authors | Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu |
| Abstract | Stochastic gradient Hamiltonian Monte Carlo (SGHMC) is a variant of stochastic gradient with momentum where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global minimum. Many works reported its empirical success in practice for solving stochastic non-convex optimization problems, in particular it has been observed to outperform overdamped Langevin Monte Carlo-based methods such as stochastic gradient Langevin dynamics (SGLD) in many applications. Although asymptotic global convergence properties of SGHMC are well known, its finite-time performance is not well-understood. In this work, we study two variants of SGHMC based on two alternative discretizations of the underdamped Langevin diffusion. We provide finite-time performance bounds for the global convergence of both SGHMC variants for solving stochastic non-convex optimization problems with explicit constants. Our results lead to non-asymptotic guarantees for both population and empirical risk minimization problems. For a fixed target accuracy level, on a class of non-convex problems, we obtain complexity bounds for SGHMC that can be tighter than those for SGLD. These results show that acceleration with momentum is possible in the context of global non-convex optimization. |
| Tasks | Stochastic Optimization |
| Published | 2018-09-12 |
| URL | https://arxiv.org/abs/1809.04618v3 |
| https://arxiv.org/pdf/1809.04618v3.pdf | |
| PWC | https://paperswithcode.com/paper/global-convergence-of-stochastic-gradient |
| Repo | |
| Framework | |
Automatic Brain Structures Segmentation Using Deep Residual Dilated U-Net
| Title | Automatic Brain Structures Segmentation Using Deep Residual Dilated U-Net |
| Authors | Hongwei Li, Andrii Zhygallo, Bjoern Menze |
| Abstract | Brain image segmentation is used for visualizing and quantifying anatomical structures of the brain. We present an automated ap-proach using 2D deep residual dilated networks which captures rich context information of different tissues for the segmentation of eight brain structures. The proposed system was evaluated in the MICCAI Brain Segmentation Challenge and ranked 9th out of 22 teams. We further compared the method with traditional U-Net using leave-one-subject-out cross-validation setting on the public dataset. Experimental results shows that the proposed method outperforms traditional U-Net (i.e. 80.9% vs 78.3% in averaged Dice score, 4.35mm vs 11.59mm in averaged robust Hausdorff distance) and is computationally efficient. |
| Tasks | Brain Image Segmentation, Brain Segmentation, Semantic Segmentation |
| Published | 2018-11-10 |
| URL | http://arxiv.org/abs/1811.04312v1 |
| http://arxiv.org/pdf/1811.04312v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-brain-structures-segmentation-using |
| Repo | |
| Framework | |
Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods
| Title | Learning from #Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods |
| Authors | Raul Gomez, Lluis Gomez, Jaume Gibert, Dimosthenis Karatzas |
| Abstract | Massive tourism is becoming a big problem for some cities, such as Barcelona, due to its concentration in some neighborhoods. In this work we gather Instagram data related to Barcelona consisting on images-captions pairs and, using the text as a supervisory signal, we learn relations between images, words and neighborhoods. Our goal is to learn which visual elements appear in photos when people is posting about each neighborhood. We perform a language separate treatment of the data and show that it can be extrapolated to a tourists and locals separate analysis, and that tourism is reflected in Social Media at a neighborhood level. The presented pipeline allows analyzing the differences between the images that tourists and locals associate to the different neighborhoods. The proposed method, which can be extended to other cities or subjects, proves that Instagram data can be used to train multi-modal (image and text) machine learning models that are useful to analyze publications about a city at a neighborhood level. We publish the collected dataset, InstaBarcelona and the code used in the analysis. |
| Tasks | |
| Published | 2018-08-20 |
| URL | http://arxiv.org/abs/1808.06369v1 |
| http://arxiv.org/pdf/1808.06369v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-barcelona-instagram-data-what |
| Repo | |
| Framework | |
An English-Hindi Code-Mixed Corpus: Stance Annotation and Baseline System
| Title | An English-Hindi Code-Mixed Corpus: Stance Annotation and Baseline System |
| Authors | Sahil Swami, Ankush Khandelwal, Vinay Singh, Syed Sarfaraz Akhtar, Manish Shrivastava |
| Abstract | Social media has become one of the main channels for peo- ple to communicate and share their views with the society. We can often detect from these views whether the person is in favor, against or neu- tral towards a given topic. These opinions from social media are very useful for various companies. We present a new dataset that consists of 3545 English-Hindi code-mixed tweets with opinion towards Demoneti- sation that was implemented in India in 2016 which was followed by a large countrywide debate. We present a baseline supervised classification system for stance detection developed using the same dataset that uses various machine learning techniques to achieve an accuracy of 58.7% on 10-fold cross validation. |
| Tasks | Stance Detection |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.11868v1 |
| http://arxiv.org/pdf/1805.11868v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-english-hindi-code-mixed-corpus-stance |
| Repo | |
| Framework | |
Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization
| Title | Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization |
| Authors | Zachary Seymour, Karan Sikka, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar |
| Abstract | We present an approach that combines appearance and semantic information for 2D image-based localization (2D-VL) across large perceptual changes and time lags. Compared to appearance features, the semantic layout of a scene is generally more invariant to appearance variations. We use this intuition and propose a novel end-to-end deep attention-based framework that utilizes multimodal cues to generate robust embeddings for 2D-VL. The proposed attention module predicts a shared channel attention and modality-specific spatial attentions to guide the embeddings to focus on more reliable image regions. We evaluate our model against state-of-the-art (SOTA) methods on three challenging localization datasets. We report an average (absolute) improvement of $19%$ over current SOTA for 2D-VL. Furthermore, we present an extensive study demonstrating the contribution of each component of our model, showing $8$–$15%$ and $4%$ improvement from adding semantic information and our proposed attention module. We finally show the predicted attention maps to offer useful insights into our model. |
| Tasks | Deep Attention, Image-Based Localization, Visual Localization |
| Published | 2018-12-08 |
| URL | https://arxiv.org/abs/1812.03402v2 |
| https://arxiv.org/pdf/1812.03402v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantically-aware-attentive-neural |
| Repo | |
| Framework | |
