Paper Group ANR 1
Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks. An Empirical Analysis of Constrained Support Vector Quantile Regression for Nonparametric Probabilistic Forecasting of Wind Power. Detecting truth, just on parts. Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks. SpaRTA - Tracking a …
Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks
| Title | Deep Inference of Personality Traits by Integrating Image and Word Use in Social Networks |
| Authors | Guillem Cucurull, Pau Rodríguez, V. Oguz Yazici, Josep M. Gonfaus, F. Xavier Roca, Jordi Gonzàlez |
| Abstract | Social media, as a major platform for communication and information exchange, is a rich repository of the opinions and sentiments of 2.3 billion users about a vast spectrum of topics. To sense the whys of certain social user’s demands and cultural-driven interests, however, the knowledge embedded in the 1.8 billion pictures which are uploaded daily in public profiles has just started to be exploited since this process has been typically been text-based. Following this trend on visual-based social analysis, we present a novel methodology based on Deep Learning to build a combined image-and-text based personality trait model, trained with images posted together with words found highly correlated to specific personality traits. So the key contribution here is to explore whether OCEAN personality trait modeling can be addressed based on images, here called \emph{Mind{P}ics}, appearing with certain tags with psychological insights. We found that there is a correlation between those posted images and their accompanying texts, which can be successfully modeled using deep neural networks for personality estimation. The experimental results are consistent with previous cyber-psychology results based on texts or images. In addition, classification results on some traits show that some patterns emerge in the set of images corresponding to a specific text, in essence to those representing an abstract concept. These results open new avenues of research for further refining the proposed personality model under the supervision of psychology experts. |
| Tasks | |
| Published | 2018-02-06 |
| URL | http://arxiv.org/abs/1802.06757v1 |
| http://arxiv.org/pdf/1802.06757v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-inference-of-personality-traits-by |
| Repo | |
| Framework | |
An Empirical Analysis of Constrained Support Vector Quantile Regression for Nonparametric Probabilistic Forecasting of Wind Power
| Title | An Empirical Analysis of Constrained Support Vector Quantile Regression for Nonparametric Probabilistic Forecasting of Wind Power |
| Authors | Kostas Hatalis, Shalinee Kishore, Katya Scheinberg, Alberto Lamadrid |
| Abstract | Uncertainty analysis in the form of probabilistic forecasting can provide significant improvements in decision-making processes in the smart power grid for better integrating renewable energies such as wind. Whereas point forecasting provides a single expected value, probabilistic forecasts provide more information in the form of quantiles, prediction intervals, or full predictive densities. This paper analyzes the effectiveness of an approach for nonparametric probabilistic forecasting of wind power that combines support vector machines and nonlinear quantile regression with non-crossing constraints. A numerical case study is conducted using publicly available wind data from the Global Energy Forecasting Competition 2014. Multiple quantiles are estimated to form 20%, 40%, 60% and 80% prediction intervals which are evaluated using the pinball loss function and reliability measures. Three benchmark models are used for comparison where results demonstrate the proposed approach leads to significantly better performance while preventing the problem of overlapping quantile estimates. |
| Tasks | Decision Making |
| Published | 2018-03-29 |
| URL | http://arxiv.org/abs/1803.10888v1 |
| http://arxiv.org/pdf/1803.10888v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-empirical-analysis-of-constrained-support |
| Repo | |
| Framework | |
Detecting truth, just on parts
| Title | Detecting truth, just on parts |
| Authors | Zoltán Kovács, Tomás Recio, M. Pilar Vélez |
| Abstract | We introduce and discuss, through a computational algebraic geometry approach, the automatic reasoning handling of propositions that are simultaneously true and false over some relevant collections of instances. A rigorous, algorithmic criterion is presented for detecting such cases, and its performance is exemplified through the implementation of this test on the dynamic geometry program GeoGebra. |
| Tasks | |
| Published | 2018-02-16 |
| URL | http://arxiv.org/abs/1802.05875v2 |
| http://arxiv.org/pdf/1802.05875v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-truth-just-on-parts |
| Repo | |
| Framework | |
Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks
| Title | Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks |
| Authors | Daniel Fojo, Víctor Campos, Xavier Giro-i-Nieto |
| Abstract | Adaptive Computation Time for Recurrent Neural Networks (ACT) is one of the most promising architectures for variable computation. ACT adapts to the input sequence by being able to look at each sample more than once, and learn how many times it should do it. In this paper, we compare ACT to Repeat-RNN, a novel architecture based on repeating each sample a fixed number of times. We found surprising results, where Repeat-RNN performs as good as ACT in the selected tasks. Source code in TensorFlow and PyTorch is publicly available at https://imatge-upc.github.io/danifojo-2018-repeatrnn/ |
| Tasks | |
| Published | 2018-03-21 |
| URL | http://arxiv.org/abs/1803.08165v1 |
| http://arxiv.org/pdf/1803.08165v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-fixed-and-adaptive-computation-time |
| Repo | |
| Framework | |
SpaRTA - Tracking across occlusions via global partitioning of 3D clouds of points
| Title | SpaRTA - Tracking across occlusions via global partitioning of 3D clouds of points |
| Authors | Andrea Cavagna, Stefania Melillo, Leonardo Parisi, Federico Ricci-Tersenghi |
| Abstract | Any 3D tracking algorithm has to deal with occlusions: multiple targets get so close to each other that the loss of their identities becomes likely. In the best case scenario, trajectories are interrupted, thus curbing the completeness of the data-set; in the worse case scenario, identity switches arise, potentially affecting in severe ways the very quality of the data. Here, we present a novel tracking method that addresses the problem of occlusions within large groups of featureless objects by means of three steps: i) it represents each target as a cloud of points in 3D; ii) once a 3D cluster corresponding to an occlusion occurs, it defines a partitioning problem by introducing a cost function that uses both attractive and repulsive spatio-temporal proximity links; iii) it minimizes the cost function through a semi-definite optimization technique specifically designed to cope with link frustration. The algorithm is independent of the specific experimental method used to collect the data. By performing tests on public data-sets, we show that the new algorithm produces a significant improvement over the state-of-the-art tracking methods, both by reducing the number of identity switches and by increasing the accuracy of the actual positions of the targets in real space. |
| Tasks | |
| Published | 2018-02-16 |
| URL | http://arxiv.org/abs/1802.05878v1 |
| http://arxiv.org/pdf/1802.05878v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparta-tracking-across-occlusions-via-global |
| Repo | |
| Framework | |
Clinically Meaningful Comparisons Over Time: An Approach to Measuring Patient Similarity based on Subsequence Alignment
| Title | Clinically Meaningful Comparisons Over Time: An Approach to Measuring Patient Similarity based on Subsequence Alignment |
| Authors | Dev Goyal, Zeeshan Syed, Jenna Wiens |
| Abstract | Longitudinal patient data has the potential to improve clinical risk stratification models for disease. However, chronic diseases that progress slowly over time are often heterogeneous in their clinical presentation. Patients may progress through disease stages at varying rates. This leads to pathophysiological misalignment over time, making it difficult to consistently compare patients in a clinically meaningful way. Furthermore, patients present clinically for the first time at different stages of disease. This eliminates the possibility of simply aligning patients based on their initial presentation. Finally, patient data may be sampled at different rates due to differences in schedules or missed visits. To address these challenges, we propose a robust measure of patient similarity based on subsequence alignment. Compared to global alignment techniques that do not account for pathophysiological misalignment, focusing on the most relevant subsequences allows for an accurate measure of similarity between patients. We demonstrate the utility of our approach in settings where longitudinal data, while useful, are limited and lack a clear temporal alignment for comparison. Applied to the task of stratifying patients for risk of progression to probable Alzheimer’s Disease, our approach outperforms models that use only snapshot data (AUROC of 0.839 vs. 0.812) and models that use global alignment techniques (AUROC of 0.822). Our results support the hypothesis that patients’ trajectories are useful for quantifying inter-patient similarities and that using subsequence matching and can help account for heterogeneity and misalignment in longitudinal data. |
| Tasks | |
| Published | 2018-03-02 |
| URL | http://arxiv.org/abs/1803.00744v1 |
| http://arxiv.org/pdf/1803.00744v1.pdf | |
| PWC | https://paperswithcode.com/paper/clinically-meaningful-comparisons-over-time |
| Repo | |
| Framework | |
Rao-Blackwellized Stochastic Gradients for Discrete Distributions
| Title | Rao-Blackwellized Stochastic Gradients for Discrete Distributions |
| Authors | Runjing Liu, Jeffrey Regier, Nilesh Tripuraneni, Michael I. Jordan, Jon McAuliffe |
| Abstract | We wish to compute the gradient of an expectation over a finite or countably infinite sample space having $K \leq \infty$ categories. When $K$ is indeed infinite, or finite but very large, the relevant summation is intractable. Accordingly, various stochastic gradient estimators have been proposed. In this paper, we describe a technique that can be applied to reduce the variance of any such estimator, without changing its bias—in particular, unbiasedness is retained. We show that our technique is an instance of Rao-Blackwellization, and we demonstrate the improvement it yields on a semi-supervised classification problem and a pixel attention task. |
| Tasks | |
| Published | 2018-10-10 |
| URL | https://arxiv.org/abs/1810.04777v3 |
| https://arxiv.org/pdf/1810.04777v3.pdf | |
| PWC | https://paperswithcode.com/paper/rao-blackwellized-stochastic-gradients-for |
| Repo | |
| Framework | |
On The Complexity of Sparse Label Propagation
| Title | On The Complexity of Sparse Label Propagation |
| Authors | Alexander Jung |
| Abstract | This paper investigates the computational complexity of sparse label propagation which has been proposed recently for processing network structured data. Sparse label propagation amounts to a convex optimization problem and might be considered as an extension of basis pursuit from sparse vectors to network structured datasets. Using a standard first-order oracle model, we characterize the number of iterations for sparse label propagation to achieve a prescribed accuracy. In particular, we derive an upper bound on the number of iterations required to achieve a certain accuracy and show that this upper bound is sharp for datasets having a chain structure (e.g., time series). |
| Tasks | Time Series |
| Published | 2018-04-25 |
| URL | http://arxiv.org/abs/1804.09597v2 |
| http://arxiv.org/pdf/1804.09597v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-complexity-of-sparse-label-propagation |
| Repo | |
| Framework | |
LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning
| Title | LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning |
| Authors | Hsin-Pai Cheng, Patrick Yu, Haojing Hu, Feng Yan, Shiyu Li, Hai Li, Yiran Chen |
| Abstract | Distributed learning systems have enabled training large-scale models over large amount of data in significantly shorter time. In this paper, we focus on decentralized distributed deep learning systems and aim to achieve differential privacy with good convergence rate and low communication cost. To achieve this goal, we propose a new learning algorithm LEASGD (Leader-Follower Elastic Averaging Stochastic Gradient Descent), which is driven by a novel Leader-Follower topology and a differential privacy model.We provide a theoretical analysis of the convergence rate and the trade-off between the performance and privacy in the private setting.The experimental results show that LEASGD outperforms state-of-the-art decentralized learning algorithm DPSGD by achieving steadily lower loss within the same iterations and by reducing the communication cost by 30%. In addition, LEASGD spends less differential privacy budget and has higher final accuracy result than DPSGD under private setting. |
| Tasks | |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11124v1 |
| http://arxiv.org/pdf/1811.11124v1.pdf | |
| PWC | https://paperswithcode.com/paper/leasgd-an-efficient-and-privacy-preserving |
| Repo | |
| Framework | |
Towards Deeper Generative Architectures for GANs using Dense connections
| Title | Towards Deeper Generative Architectures for GANs using Dense connections |
| Authors | Samarth Tripathi, Renbo Tu |
| Abstract | In this paper, we present the result of adopting skip connections and dense layers, previously used in image classification tasks, in the Fisher GAN implementation. We have experimented with different numbers of layers and inserting these connections in different sections of the network. Our findings suggests that networks implemented with the connections produce better images than the baseline, and the number of connections added has only slight effect on the result. |
| Tasks | Image Classification |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1804.11031v2 |
| http://arxiv.org/pdf/1804.11031v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-deeper-generative-architectures-for |
| Repo | |
| Framework | |
Classifying Patent Applications with Ensemble Methods
| Title | Classifying Patent Applications with Ensemble Methods |
| Authors | Fernando Benites, Shervin Malmasi, Marcos Zampieri |
| Abstract | We present methods for the automatic classification of patent applications using an annotated dataset provided by the organizers of the ALTA 2018 shared task - Classifying Patent Applications. The goal of the task is to use computational methods to categorize patent applications according to a coarse-grained taxonomy of eight classes based on the International Patent Classification (IPC). We tested a variety of approaches for this task and the best results, 0.778 micro-averaged F1-Score, were achieved by SVM ensembles using a combination of words and characters as features. Our team, BMZ, was ranked first among 14 teams in the competition. |
| Tasks | |
| Published | 2018-11-12 |
| URL | http://arxiv.org/abs/1811.04695v1 |
| http://arxiv.org/pdf/1811.04695v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-patent-applications-with-ensemble |
| Repo | |
| Framework | |
Propagation Networks for Model-Based Control Under Partial Observation
| Title | Propagation Networks for Model-Based Control Under Partial Observation |
| Authors | Yunzhu Li, Jiajun Wu, Jun-Yan Zhu, Joshua B. Tenenbaum, Antonio Torralba, Russ Tedrake |
| Abstract | There has been an increasing interest in learning dynamics simulators for model-based control. Compared with off-the-shelf physics engines, a learnable simulator can quickly adapt to unseen objects, scenes, and tasks. However, existing models like interaction networks only work for fully observable systems; they also only consider pairwise interactions within a single time step, both restricting their use in practical systems. We introduce Propagation Networks (PropNet), a differentiable, learnable dynamics model that handles partially observable scenarios and enables instantaneous propagation of signals beyond pairwise interactions. Experiments show that our propagation networks not only outperform current learnable physics engines in forward simulation, but also achieve superior performance on various control tasks. Compared with existing model-free deep reinforcement learning algorithms, model-based control with propagation networks is more accurate, efficient, and generalizable to new, partially observable scenes and tasks. |
| Tasks | |
| Published | 2018-09-28 |
| URL | http://arxiv.org/abs/1809.11169v2 |
| http://arxiv.org/pdf/1809.11169v2.pdf | |
| PWC | https://paperswithcode.com/paper/propagation-networks-for-model-based-control |
| Repo | |
| Framework | |
Learning to Assemble Neural Module Tree Networks for Visual Grounding
| Title | Learning to Assemble Neural Module Tree Networks for Visual Grounding |
| Authors | Daqing Liu, Hanwang Zhang, Feng Wu, Zheng-Jun Zha |
| Abstract | Visual grounding, a task to ground (i.e., localize) natural language in images, essentially requires composite visual reasoning. However, existing methods over-simplify the composite nature of language into a monolithic sentence embedding or a coarse composition of subject-predicate-object triplet. In this paper, we propose to ground natural language in an intuitive, explainable, and composite fashion as it should be. In particular, we develop a novel modular network called Neural Module Tree network (NMTree) that regularizes the visual grounding along the dependency parsing tree of the sentence, where each node is a neural module that calculates visual attention according to its linguistic feature, and the grounding score is accumulated in a bottom-up direction where as needed. NMTree disentangles the visual grounding from the composite reasoning, allowing the former to only focus on primitive and easy-to-generalize patterns. To reduce the impact of parsing errors, we train the modules and their assembly end-to-end by using the Gumbel-Softmax approximation and its straight-through gradient estimator, accounting for the discrete nature of module assembly. Overall, the proposed NMTree consistently outperforms the state-of-the-arts on several benchmarks. Qualitative results show explainable grounding score calculation in great detail. |
| Tasks | Dependency Parsing, Natural Language Visual Grounding, Sentence Embedding, Visual Reasoning |
| Published | 2018-12-08 |
| URL | https://arxiv.org/abs/1812.03299v3 |
| https://arxiv.org/pdf/1812.03299v3.pdf | |
| PWC | https://paperswithcode.com/paper/explainability-by-parsing-neural-module-tree |
| Repo | |
| Framework | |
Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference
| Title | Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference |
| Authors | Jeffrey L. McKinstry, Steven K. Esser, Rathinakumar Appuswamy, Deepika Bablani, John V. Arthur, Izzet B. Yildiz, Dharmendra S. Modha |
| Abstract | To realize the promise of ubiquitous embedded deep network inference, it is essential to seek limits of energy and area efficiency. To this end, low-precision networks offer tremendous promise because both energy and area scale down quadratically with the reduction in precision. Here we demonstrate ResNet-18, -34, -50, -152, Inception-v3, Densenet-161, and VGG-16bn networks on the ImageNet classification benchmark that, at 8-bit precision exceed the accuracy of the full-precision baseline networks after one epoch of finetuning, thereby leveraging the availability of pretrained models. We also demonstrate ResNet-18, -34, -50, -152, Densenet-161, and VGG-16bn 4-bit models that match the accuracy of the full-precision baseline networks – the highest scores to date. Surprisingly, the weights of the low-precision networks are very close (in cosine similarity) to the weights of the corresponding baseline networks, making training from scratch unnecessary. We find that gradient noise due to quantization during training increases with reduced precision, and seek ways to overcome this noise. The number of iterations required by SGD to achieve a given training error is related to the square of (a) the distance of the initial solution from the final plus (b) the maximum variance of the gradient estimates. Therefore, we (a) reduce solution distance by starting with pretrained fp32 precision baseline networks and fine-tuning, and (b) combat gradient noise introduced by quantization by training longer and reducing learning rates. Sensitivity analysis indicates that these simple techniques, coupled with proper activation function range calibration to take full advantage of the limited precision, are sufficient to discover low-precision networks, if they exist, close to fp32 precision baseline networks. The results herein provide evidence that 4-bits suffice for classification. |
| Tasks | Calibration, Quantization |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.04191v2 |
| http://arxiv.org/pdf/1809.04191v2.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-low-precision-networks-close-to |
| Repo | |
| Framework | |
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
| Title | NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation |
| Authors | Hui Su, Xiaoyu Shen, Wenjie Li, Dietrich Klakow |
| Abstract | Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of human-computer communications, they suffer from the problem of strongly favoring short generic responses. In this paper, we argue that a good response should smoothly connect both the preceding dialogue history and the following conversations. We strengthen this connection through mutual information maximization. To sidestep the non-differentiability of discrete natural language tokens, we introduce an auxiliary continuous code space and map such code space to a learnable prior distribution for generation purpose. Experiments on two dialogue datasets validate the effectiveness of our model, where the generated responses are closely related to the dialogue context and lead to more interactive conversations. |
| Tasks | Dialogue Generation |
| Published | 2018-09-27 |
| URL | http://arxiv.org/abs/1810.00671v2 |
| http://arxiv.org/pdf/1810.00671v2.pdf | |
| PWC | https://paperswithcode.com/paper/nexus-network-connecting-the-preceding-and |
| Repo | |
| Framework | |
