Paper Group ANR 1011
Path Capsule Networks. AMD Severity Prediction And Explainability Using Image Registration And Deep Embedded Clustering. Topological Interpretation of Interactive Computation. Active and Passive Portfolio Management with Latent Factors. A collaborative filtering model with heterogeneous neural networks for recommender systems. Classifying Partially …
Path Capsule Networks
| Title | Path Capsule Networks |
| Authors | Mohammed Amer, Tomás Maul |
| Abstract | Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter’s invariance properties with equivariance through pose estimation. CapsNet achieved a very decent performance with a shallow architecture and a significant reduction in parameters count. However, the width of the first layer in CapsNet is still contributing to a significant number of its parameters and the shallowness may be limiting the representational power of the capsules. To address these limitations, we introduce Path Capsule Network (PathCapsNet), a deep parallel multi-path version of CapsNet. We show that a judicious coordination of depth, max-pooling, regularization by DropCircuit and a new fan-in routing by agreement technique can achieve better or comparable results to CapsNet, while further reducing the parameter count significantly. |
| Tasks | Pose Estimation |
| Published | 2019-02-11 |
| URL | https://arxiv.org/abs/1902.03760v2 |
| https://arxiv.org/pdf/1902.03760v2.pdf | |
| PWC | https://paperswithcode.com/paper/path-capsule-networks |
| Repo | |
| Framework | |
AMD Severity Prediction And Explainability Using Image Registration And Deep Embedded Clustering
| Title | AMD Severity Prediction And Explainability Using Image Registration And Deep Embedded Clustering |
| Authors | Dwarikanath Mahapatra |
| Abstract | We propose a method to predict severity of age related macular degeneration (AMD) from input optical coherence tomography (OCT) images. Although there is no standard clinical severity scale for AMD, we leverage deep learning (DL) based image registration and clustering methods to identify diseased cases and predict their severity. Experiments demonstrate our approach’s disease classification performance matches state of the art methods. The predicted disease severity performs well on previously unseen data. Registration output provides better explainability than class activation maps regarding label and severity decisions |
| Tasks | Image Registration |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03075v1 |
| https://arxiv.org/pdf/1907.03075v1.pdf | |
| PWC | https://paperswithcode.com/paper/amd-severity-prediction-and-explainability |
| Repo | |
| Framework | |
Topological Interpretation of Interactive Computation
| Title | Topological Interpretation of Interactive Computation |
| Authors | Emanuela Merelli, Anita Wasilewska |
| Abstract | It is a great pleasure to write this tribute in honor of Scott A. Smolka on his 65th birthday. We revisit Goldin, Smolka hypothesis that persistent Turing machine (PTM) can capture the intuitive notion of sequential interaction computation. We propose a topological setting to model the abstract concept of environment. We use it to define a notion of a topological Turing machine (TTM) as a universal model for interactive computation and possible model for concurrent computation. |
| Tasks | |
| Published | 2019-08-03 |
| URL | https://arxiv.org/abs/1908.04264v1 |
| https://arxiv.org/pdf/1908.04264v1.pdf | |
| PWC | https://paperswithcode.com/paper/topological-interpretation-of-interactive |
| Repo | |
| Framework | |
Active and Passive Portfolio Management with Latent Factors
| Title | Active and Passive Portfolio Management with Latent Factors |
| Authors | Ali Al-Aradi, Sebastian Jaimungal |
| Abstract | We address a portfolio selection problem that combines active (outperformance) and passive (tracking) objectives using techniques from convex analysis. We assume a general semimartingale market model where the assets’ growth rate processes are driven by a latent factor. Using techniques from convex analysis we obtain a closed-form solution for the optimal portfolio and provide a theorem establishing its uniqueness. The motivation for incorporating latent factors is to achieve improved growth rate estimation, an otherwise notoriously difficult task. To this end, we focus on a model where growth rates are driven by an unobservable Markov chain. The solution in this case requires a filtering step to obtain posterior probabilities for the state of the Markov chain from asset price information, which are subsequently used to find the optimal allocation. We show the optimal strategy is the posterior average of the optimal strategies the investor would have held in each state assuming the Markov chain remains in that state. Finally, we implement a number of historical backtests to demonstrate the performance of the optimal portfolio. |
| Tasks | |
| Published | 2019-03-16 |
| URL | http://arxiv.org/abs/1903.06928v1 |
| http://arxiv.org/pdf/1903.06928v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-and-passive-portfolio-management-with |
| Repo | |
| Framework | |
A collaborative filtering model with heterogeneous neural networks for recommender systems
| Title | A collaborative filtering model with heterogeneous neural networks for recommender systems |
| Authors | Ge Fan, Wei Zeng, Shan Sun, Biao Geng, Weiyi Wang, Weibo Liu |
| Abstract | In recent years, deep neural network is introduced in recommender systems to solve the collaborative filtering problem, which has achieved immense success on computer vision, speech recognition and natural language processing. On one hand, deep neural network can be used to model the auxiliary information in recommender systems. On the other hand, it is also capable of modeling nonlinear relationships between users and items. One advantage of deep neural network is that the performance of the algorithm can be easily enhanced by augmenting the depth of the neural network. However, two potential problems may emerge when the deep neural work is exploited to model relationships between users and items. The fundamental problem is that the complexity of the algorithm grows significantly with the increment in the depth of the neural network. The second one is that a deeper neural network may undermine the accuracy of the algorithm. In order to alleviate these problems, we propose a hybrid neural network that combines heterogeneous neural networks with different structures. The experimental results on real datasets reveal that our method is superior to the state-of-the-art methods in terms of the item ranking. |
| Tasks | Recommendation Systems, Speech Recognition |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11133v2 |
| https://arxiv.org/pdf/1905.11133v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-collaborative-filtering-model-with |
| Repo | |
| Framework | |
Classifying Partially Labeled Networked Data via Logistic Network Lasso
| Title | Classifying Partially Labeled Networked Data via Logistic Network Lasso |
| Authors | Nguyen Tran, Henrik Ambos, Alexander Jung |
| Abstract | We apply the network Lasso to classify partially labeled data points which are characterized by high-dimensional feature vectors. In order to learn an accurate classifier from limited amounts of labeled data, we borrow statistical strength, via an intrinsic network structure, across the dataset. The resulting logistic network Lasso amounts to a regularized empirical risk minimization problem using the total variation of a classifier as a regularizer. This minimization problem is a non-smooth convex optimization problem which we solve using a primal-dual splitting method. This method is appealing for big data applications as it can be implemented as a highly scalable message passing algorithm. |
| Tasks | |
| Published | 2019-03-26 |
| URL | http://arxiv.org/abs/1903.10926v1 |
| http://arxiv.org/pdf/1903.10926v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-partially-labeled-networked-data |
| Repo | |
| Framework | |
DNN Architecture for High Performance Prediction on Natural Videos Loses Submodule’s Ability to Learn Discrete-World Dataset
| Title | DNN Architecture for High Performance Prediction on Natural Videos Loses Submodule’s Ability to Learn Discrete-World Dataset |
| Authors | Lana Sinapayen, Atsushi Noda |
| Abstract | Is cognition a collection of loosely connected functions tuned to different tasks, or can there be a general learning algorithm? If such an hypothetical general algorithm did exist, tuned to our world, could it adapt seamlessly to a world with different laws of nature? We consider the theory that predictive coding is such a general rule, and falsify it for one specific neural architecture known for high-performance predictions on natural videos and replication of human visual illusions: PredNet. Our results show that PredNet’s high performance generalizes without retraining on a completely different natural video dataset. Yet PredNet cannot be trained to reach even mediocre accuracy on an artificial video dataset created with the rules of the Game of Life (GoL). We also find that a submodule of PredNet, a Convolutional Neural Network trained alone, reaches perfect accuracy on the GoL while being mediocre for natural videos, showing that PredNet’s architecture itself is responsible for both the high performance on natural videos and the loss of performance on the GoL. Just as humans cannot predict the dynamics of the GoL, our results suggest that there might be a trade-off between high performance on sensory inputs with different sets of rules. |
| Tasks | |
| Published | 2019-04-16 |
| URL | http://arxiv.org/abs/1904.07969v1 |
| http://arxiv.org/pdf/1904.07969v1.pdf | |
| PWC | https://paperswithcode.com/paper/dnn-architecture-for-high-performance |
| Repo | |
| Framework | |
Shared Generative Latent Representation Learning for Multi-view Clustering
| Title | Shared Generative Latent Representation Learning for Multi-view Clustering |
| Authors | Ming Yin, Weitian Huang, Junbin Gao |
| Abstract | Clustering multi-view data has been a fundamental research topic in the computer vision community. It has been shown that a better accuracy can be achieved by integrating information of all the views than just using one view individually. However, the existing methods often struggle with the issues of dealing with the large-scale datasets and the poor performance in reconstructing samples. This paper proposes a novel multi-view clustering method by learning a shared generative latent representation that obeys a mixture of Gaussian distributions. The motivation is based on the fact that the multi-view data share a common latent embedding despite the diversity among the views. Specifically, benefited from the success of the deep generative learning, the proposed model not only can extract the nonlinear features from the views, but render a powerful ability in capturing the correlations among all the views. The extensive experimental results, on several datasets with different scales, demonstrate that the proposed method outperforms the state-of-the-art methods under a range of performance criteria. |
| Tasks | Representation Learning |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09747v1 |
| https://arxiv.org/pdf/1907.09747v1.pdf | |
| PWC | https://paperswithcode.com/paper/shared-generative-latent-representation |
| Repo | |
| Framework | |
Sequential Recommendation with Relation-Aware Kernelized Self-Attention
| Title | Sequential Recommendation with Relation-Aware Kernelized Self-Attention |
| Authors | Mingi Ji, Weonyoung Joo, Kyungwoo Song, Yoon-Yeong Kim, Il-Chul Moon |
| Abstract | Recent studies identified that sequential Recommendation is improved by the attention mechanism. By following this development, we propose Relation-Aware Kernelized Self-Attention (RKSA) adopting a self-attention mechanism of the Transformer with augmentation of a probabilistic model. The original self-attention of Transformer is a deterministic measure without relation-awareness. Therefore, we introduce a latent space to the self-attention, and the latent space models the recommendation context from relation as a multivariate skew-normal distribution with a kernelized covariance matrix from co-occurrences, item characteristics, and user information. This work merges the self-attention of the Transformer and the sequential recommendation by adding a probabilistic model of the recommendation task specifics. We experimented RKSA over the benchmark datasets, and RKSA shows significant improvements compared to the recent baseline models. Also, RKSA were able to produce a latent space model that answers the reasons for recommendation. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06478v1 |
| https://arxiv.org/pdf/1911.06478v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequential-recommendation-with-relation-aware |
| Repo | |
| Framework | |
Towards Efficient and Secure Delivery of Data for Deep Learning with Privacy-Preserving
| Title | Towards Efficient and Secure Delivery of Data for Deep Learning with Privacy-Preserving |
| Authors | Juncheng Shen, Juzheng Liu, Yiran Chen, Hai Li |
| Abstract | Privacy recently emerges as a severe concern in deep learning, that is, sensitive data must be prohibited from being shared with the third party during deep neural network development. In this paper, we propose Morphed Learning (MoLe), an efficient and secure scheme to deliver deep learning data. MoLe has two main components: data morphing and Augmented Convolutional (Aug-Conv) layer. Data morphing allows data providers to send morphed data without privacy information, while Aug-Conv layer helps deep learning developers to apply their networks on the morphed data without performance penalty. MoLe provides stronger security while introducing lower overhead compared to GAZELLE (USENIX Security 2018), which is another method with no performance penalty on the neural network. When using MoLe for VGG-16 network on CIFAR dataset, the computational overhead is only 9% and the data transmission overhead is 5.12%. As a comparison, GAZELLE has computational overhead of 10,000 times and data transmission overhead of 421,000 times. In this setting, the attack success rate of adversary is 7.9 x 10^{-90} for MoLe and 2.9 x 10^{-30} for GAZELLE, respectively. |
| Tasks | |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07632v1 |
| https://arxiv.org/pdf/1909.07632v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-efficient-and-secure-delivery-of-data |
| Repo | |
| Framework | |
Average-Case Lower Bounds for Learning Sparse Mixtures, Robust Estimation and Semirandom Adversaries
| Title | Average-Case Lower Bounds for Learning Sparse Mixtures, Robust Estimation and Semirandom Adversaries |
| Authors | Matthew Brennan, Guy Bresler |
| Abstract | This paper develops several average-case reduction techniques to show new hardness results for three central high-dimensional statistics problems, implying a statistical-computational gap induced by robustness, a detection-recovery gap and a universality principle for these gaps. A main feature of our approach is to map to these problems via a common intermediate problem that we introduce, which we call Imbalanced Sparse Gaussian Mixtures. We assume the planted clique conjecture for a version of the planted clique problem where the position of the planted clique is mildly constrained, and from this obtain the following computational lower bounds: (1) a $k$-to-$k^2$ statistical-computational gap for robust sparse mean estimation, providing the first average-case evidence for a conjecture of Li (2017) and Balakrishnan et al. (2017); (2) a tight lower bound for semirandom planted dense subgraph, which shows that a semirandom adversary shifts the detection threshold in planted dense subgraph to the conjectured recovery threshold; and (3) a universality principle for $k$-to-$k^2$ gaps in a broad class of sparse mixture problems that includes many natural formulations such as the spiked covariance model. Our main approach is to introduce several average-case techniques to produce structured and Gaussianized versions of an input graph problem, and then to rotate these high-dimensional Gaussians by matrices carefully constructed from hyperplanes in $\mathbb{F}_r^t$. For our universality result, we introduce a new method to perform an algorithmic change of measure tailored to sparse mixtures. We also provide evidence that the mild promise in our variant of planted clique does not change the complexity of the problem. |
| Tasks | |
| Published | 2019-08-08 |
| URL | https://arxiv.org/abs/1908.06130v1 |
| https://arxiv.org/pdf/1908.06130v1.pdf | |
| PWC | https://paperswithcode.com/paper/average-case-lower-bounds-for-learning-sparse |
| Repo | |
| Framework | |
DoPAMINE: Double-sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling
| Title | DoPAMINE: Double-sided Masked CNN for Pixel Adaptive Multiplicative Noise Despeckling |
| Authors | Sunghwan Joo, Sungmin Cha, Taesup Moon |
| Abstract | We propose DoPAMINE, a new neural network based multiplicative noise despeckling algorithm. Our algorithm is inspired by Neural AIDE (N-AIDE), which is a recently proposed neural adaptive image denoiser. While the original N-AIDE was designed for the additive noise case, we show that the same framework, i.e., adaptively learning a network for pixel-wise affine denoisers by minimizing an unbiased estimate of MSE, can be applied to the multiplicative noise case as well. Moreover, we derive a double-sided masked CNN architecture which can control the variance of the activation values in each layer and converge fast to high denoising performance during supervised training. In the experimental results, we show our DoPAMINE possesses high adaptivity via fine-tuning the network parameters based on the given noisy image and achieves significantly better despeckling results compared to SAR-DRN, a state-of-the-art CNN-based algorithm. |
| Tasks | Denoising |
| Published | 2019-02-07 |
| URL | http://arxiv.org/abs/1902.02530v1 |
| http://arxiv.org/pdf/1902.02530v1.pdf | |
| PWC | https://paperswithcode.com/paper/dopamine-double-sided-masked-cnn-for-pixel |
| Repo | |
| Framework | |
Bayesian Exploration with Heterogeneous Agents
| Title | Bayesian Exploration with Heterogeneous Agents |
| Authors | Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins, Zhiwei Steven Wu |
| Abstract | It is common in recommendation systems that users both consume and produce information as they make strategic choices under uncertainty. While a social planner would balance “exploration” and “exploitation” using a multi-armed bandit algorithm, users’ incentives may tilt this balance in favor of exploitation. We consider Bayesian Exploration: a simple model in which the recommendation system (the “principal”) controls the information flow to the users (the “agents”) and strives to incentivize exploration via information asymmetry. A single round of this model is a version of a well-known “Bayesian Persuasion game” from [Kamenica and Gentzkow]. We allow heterogeneous users, relaxing a major assumption from prior work that users have the same preferences from one time step to another. The goal is now to learn the best personalized recommendations. One particular challenge is that it may be impossible to incentivize some of the user types to take some of the actions, no matter what the principal does or how much time she has. We consider several versions of the model, depending on whether and when the user types are reported to the principal, and design a near-optimal “recommendation policy” for each version. We also investigate how the model choice and the diversity of user types impact the set of actions that can possibly be “explored” by each type. |
| Tasks | Recommendation Systems |
| Published | 2019-02-19 |
| URL | http://arxiv.org/abs/1902.07119v1 |
| http://arxiv.org/pdf/1902.07119v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-exploration-with-heterogeneous |
| Repo | |
| Framework | |
Object-based multi-temporal and multi-source land cover mapping leveraging hierarchical class relationships
| Title | Object-based multi-temporal and multi-source land cover mapping leveraging hierarchical class relationships |
| Authors | Yawogan Jean Eudes Gbodjo, Dino Ienco, Louise Leroux, Roberto Interdonato, Raffaele Gaetano, Babacar Ndao, Stephane Dupuy |
| Abstract | European satellite missions Sentinel-1 (S1) and Sentinel-2 (S2) provide at highspatial resolution and high revisit time, respectively, radar and optical imagesthat support a wide range of Earth surface monitoring tasks such as LandUse/Land Cover mapping. A long-standing challenge in the remote sensingcommunity is about how to efficiently exploit multiple sources of information and leverage their complementary. In this particular case, get the most out ofradar and optical satellite image time series (SITS). Here, we propose to dealwith land cover mapping through a deep learning framework especially tailoredto leverage the multi-source complementarity provided by radar and opticalSITS. The proposed architecture is based on an extension of Recurrent NeuralNetwork (RNN) enriched via a customized attention mechanism capable to fitthe specificity of SITS data. In addition, we propose a new pretraining strategythat exploits domain expert knowledge to guide the model parameter initial-ization. Thorough experimental evaluations involving several machine learningcompetitors, on two contrasted study sites, have demonstrated the suitabilityof our new attention mechanism combined with the extend RNN model as wellas the benefit/limit to inject domain expert knowledge in the neural networktraining process. |
| Tasks | Time Series |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08815v1 |
| https://arxiv.org/pdf/1911.08815v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-based-multi-temporal-and-multi-source |
| Repo | |
| Framework | |
Defending from adversarial examples with a two-stream architecture
| Title | Defending from adversarial examples with a two-stream architecture |
| Authors | Hao Ge, Xiaoguang Tu, Mei Xie, Zheng Ma |
| Abstract | In recent years, deep learning has shown impressive performance on many tasks. However, recent researches showed that deep learning systems are vulnerable to small, specially crafted perturbations that are imperceptible to humans. Images with such perturbations are the so called adversarial examples, which have proven to be an indisputable threat to the DNN based applications. The lack of better understanding of the DNNs has prevented the development of efficient defenses against adversarial examples. In this paper, we propose a two-stream architecture to protect CNN from attacking by adversarial examples. Our model draws on the idea of “two-stream” which commonly used in the security field, and successfully defends different kinds of attack methods by the differences of “high-resolution” and “low-resolution” networks in feature extraction. We provide a reasonable interpretation on why our two-stream architecture is difficult to defeat, and show experimentally that our method is hard to defeat with state-of-the-art attacks. We demonstrate that our two-stream architecture is robust to adversarial examples built by currently known attacking algorithms. |
| Tasks | |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12859v1 |
| https://arxiv.org/pdf/1912.12859v1.pdf | |
| PWC | https://paperswithcode.com/paper/defending-from-adversarial-examples-with-a |
| Repo | |
| Framework | |
