Paper Group AWR 142
Privacy-Preserving Obfuscation of Critical Infrastructure Networks. Addressing Marketing Bias in Product Recommendations. Multi-view Information-theoretic Co-clustering for Co-occurrence Data. D2-Net: A Trainable CNN for Joint Detection and Description of Local Features. The Second Conversational Intelligence Challenge (ConvAI2). Towards Characteri …
Privacy-Preserving Obfuscation of Critical Infrastructure Networks
| Title | Privacy-Preserving Obfuscation of Critical Infrastructure Networks |
| Authors | Ferdinando Fioretto, Terrence W. K. Mak, Pascal Van Hentenryck |
| Abstract | The paper studies how to release data about a critical infrastructure network (e.g., the power network or a transportation network) without disclosing sensitive information that can be exploited by malevolent agents, while preserving the realism of the network. It proposes a novel obfuscation mechanism that combines several privacy-preserving building blocks with a bi-level optimization model to significantly improve accuracy. The obfuscation is evaluated for both realism and privacy properties on real energy and transportation networks. Experimental results show the obfuscation mechanism substantially reduces the potential damage of an attack exploiting the released data to harm the real network. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09778v2 |
| https://arxiv.org/pdf/1905.09778v2.pdf | |
| PWC | https://paperswithcode.com/paper/privacy-preserving-obfuscation-of-critical |
| Repo | https://github.com/Chrisackerman1/Privacy-Preserving-Obfuscation-of-Critical-Infrastructure-Networks |
| Framework | none |
Addressing Marketing Bias in Product Recommendations
| Title | Addressing Marketing Bias in Product Recommendations |
| Authors | Mengting Wan, Jianmo Ni, Rishabh Misra, Julian McAuley |
| Abstract | Modern collaborative filtering algorithms seek to provide personalized product recommendations by uncovering patterns in consumer-product interactions. However, these interactions can be biased by how the product is marketed, for example due to the selection of a particular human model in a product image. These correlations may result in the underrepresentation of particular niche markets in the interaction data; for example, a female user who would potentially like motorcycle products may be less likely to interact with them if they are promoted using stereotypically ‘male’ images. In this paper, we first investigate this correlation between users’ interaction feedback and products’ marketing images on two real-world e-commerce datasets. We further examine the response of several standard collaborative filtering algorithms to the distribution of consumer-product market segments in the input interaction data, revealing that marketing strategy can be a source of bias for modern recommender systems. In order to protect recommendation performance on underrepresented market segments, we develop a framework to address this potential marketing bias. Quantitative results demonstrate that the proposed approach significantly improves the recommendation fairness across different market segments, with a negligible loss (or better) recommendation accuracy. |
| Tasks | Recommendation Systems |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01799v1 |
| https://arxiv.org/pdf/1912.01799v1.pdf | |
| PWC | https://paperswithcode.com/paper/addressing-marketing-bias-in-product |
| Repo | https://github.com/MengtingWan/marketBias |
| Framework | tf |
Multi-view Information-theoretic Co-clustering for Co-occurrence Data
| Title | Multi-view Information-theoretic Co-clustering for Co-occurrence Data |
| Authors | Peng Xu, Zhaohong Deng, Kup-Sze Choi, Longbing Cao, Shitong Wang |
| Abstract | Multi-view clustering has received much attention recently. Most of the existing multi-view clustering methods only focus on one-sided clustering. As the co-occurring data elements involve the counts of sample-feature co-occurrences, it is more efficient to conduct two-sided clustering along the samples and features simultaneously. To take advantage of two-sided clustering for the co-occurrences in the scene of multi-view clustering, a two-sided multi-view clustering method is proposed, i.e., multi-view information-theoretic co-clustering (MV-ITCC). The proposed method realizes two-sided clustering for co-occurring multi-view data under the formulation of information theory. More specifically, it exploits the agreement and disagreement among views by sharing a common clustering results along the sample dimension and keeping the clustering results of each view specific along the feature dimension. In addition, the mechanism of maximum entropy is also adopted to control the importance of different views, which can give a right balance in leveraging the agreement and disagreement. Extensive experiments are conducted on text and image multi-view datasets. The results clearly demonstrate the superiority of the proposed method. |
| Tasks | |
| Published | 2019-05-25 |
| URL | https://arxiv.org/abs/1905.10594v1 |
| https://arxiv.org/pdf/1905.10594v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-information-theoretic-co |
| Repo | https://github.com/DallasBuyer/MVITCC |
| Framework | none |
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
| Title | D2-Net: A Trainable CNN for Joint Detection and Description of Local Features |
| Authors | Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler |
| Abstract | In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector. By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counterparts based on early detection of low-level structures. We show that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any further annotations. The proposed method obtains state-of-the-art performance on both the difficult Aachen Day-Night localization dataset and the InLoc indoor localization benchmark, as well as competitive performance on other benchmarks for image matching and 3D reconstruction. |
| Tasks | 3D Reconstruction |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03561v1 |
| https://arxiv.org/pdf/1905.03561v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503561 |
| Repo | https://github.com/mihaidusmanu/d2-net |
| Framework | pytorch |
The Second Conversational Intelligence Challenge (ConvAI2)
| Title | The Second Conversational Intelligence Challenge (ConvAI2) |
| Authors | Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, Shrimai Prabhumoye, Alan W Black, Alexander Rudnicky, Jason Williams, Joelle Pineau, Mikhail Burtsev, Jason Weston |
| Abstract | We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots. Some key takeaways from the competition are: (i) pretrained Transformer variants are currently the best performing models on this task, (ii) but to improve performance on multi-turn conversations with humans, future systems must go beyond single word metrics like perplexity to measure the performance across sequences of utterances (conversations) – in terms of repetition, consistency and balance of dialogue acts (e.g. how many questions asked vs. answered). |
| Tasks | |
| Published | 2019-01-31 |
| URL | http://arxiv.org/abs/1902.00098v1 |
| http://arxiv.org/pdf/1902.00098v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-second-conversational-intelligence |
| Repo | https://github.com/DeepPavlov/convai |
| Framework | pytorch |
Towards Characterizing and Limiting Information Exposure in DNN Layers
| Title | Towards Characterizing and Limiting Information Exposure in DNN Layers |
| Authors | Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Andrea Cavallaro, Hamed Haddadi |
| Abstract | Pre-trained Deep Neural Network (DNN) models are increasingly used in smartphones and other user devices to enable prediction services, leading to potential disclosures of (sensitive) information from training data captured inside these models. Based on the concept of generalization error, we propose a framework to measure the amount of sensitive information memorized in each layer of a DNN. Our results show that, when considered individually, the last layers encode a larger amount of information from the training data compared to the first layers. We find that, while the neuron of convolutional layers can expose more (sensitive) information than that of fully connected layers, the same DNN architecture trained with different datasets has similar exposure per layer. We evaluate an architecture to protect the most sensitive layers within the memory limits of Trusted Execution Environment (TEE) against potential white-box membership inference attacks without the significant computational overhead. |
| Tasks | |
| Published | 2019-07-13 |
| URL | https://arxiv.org/abs/1907.06034v1 |
| https://arxiv.org/pdf/1907.06034v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-characterizing-and-limiting |
| Repo | https://github.com/mofanv/darknetp |
| Framework | none |
Transfer Learning by Modeling a Distribution over Policies
| Title | Transfer Learning by Modeling a Distribution over Policies |
| Authors | Disha Shrivastava, Eeshan Gunesh Dhekane, Riashat Islam |
| Abstract | Exploration and adaptation to new tasks in a transfer learning setup is a central challenge in reinforcement learning. In this work, we build on the idea of modeling a distribution over policies in a Bayesian deep reinforcement learning setup to propose a transfer strategy. Recent works have shown to induce diversity in the learned policies by maximizing the entropy of a distribution of policies (Bachman et al., 2018; Garnelo et al., 2018) and thus, we postulate that our proposed approach leads to faster exploration resulting in improved transfer learning. We support our hypothesis by demonstrating favorable experimental results on a variety of settings on fully-observable GridWorld and partially observable MiniGrid (Chevalier-Boisvert et al., 2018) environments. |
| Tasks | Transfer Learning |
| Published | 2019-06-09 |
| URL | https://arxiv.org/abs/1906.03574v1 |
| https://arxiv.org/pdf/1906.03574v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-by-modeling-a-distribution |
| Repo | https://github.com/maximecb/gym-minigrid |
| Framework | pytorch |
Convergent Policy Optimization for Safe Reinforcement Learning
| Title | Convergent Policy Optimization for Safe Reinforcement Learning |
| Authors | Ming Yu, Zhuoran Yang, Mladen Kolar, Zhaoran Wang |
| Abstract | We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For such a problem, we construct a sequence of surrogate convex constrained optimization problems by replacing the nonconvex functions locally with convex quadratic functions obtained from policy gradient estimators. We prove that the solutions to these surrogate problems converge to a stationary point of the original nonconvex problem. Furthermore, to extend our theoretical results, we apply our algorithm to examples of optimal control and multi-agent reinforcement learning with safety constraints. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12156v1 |
| https://arxiv.org/pdf/1910.12156v1.pdf | |
| PWC | https://paperswithcode.com/paper/convergent-policy-optimization-for-safe |
| Repo | https://github.com/ming93/Safe_reinforcement_learning |
| Framework | none |
An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis
| Title | An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis |
| Authors | Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier |
| Abstract | Aspect-based sentiment analysis produces a list of aspect terms and their corresponding sentiments for a natural language sentence. This task is usually done in a pipeline manner, with aspect term extraction performed first, followed by sentiment predictions toward the extracted aspect terms. While easier to develop, such an approach does not fully exploit joint information from the two subtasks and does not use all available sources of training information that might be helpful, such as document-level labeled sentiment corpus. In this paper, we propose an interactive multi-task learning network (IMN) which is able to jointly learn multiple related tasks simultaneously at both the token level as well as the document level. Unlike conventional multi-task learning methods that rely on learning common features for the different tasks, IMN introduces a message passing architecture where information is iteratively passed to different tasks through a shared set of latent variables. Experimental results demonstrate superior performance of the proposed method against multiple baselines on three benchmark datasets. |
| Tasks | Aspect-Based Sentiment Analysis, Multi-Task Learning, Sentiment Analysis |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06906v1 |
| https://arxiv.org/pdf/1906.06906v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-interactive-multi-task-learning-network |
| Repo | https://github.com/ruidan/IMN-E2E-ABSA |
| Framework | tf |
Generative Adversarial Minority Oversampling
| Title | Generative Adversarial Minority Oversampling |
| Authors | Sankha Subhra Mullick, Shounak Datta, Swagatam Das |
| Abstract | Class imbalance is a long-standing problem relevant to a number of real-world applications of deep learning. Oversampling techniques, which are effective for handling class imbalance in classical learning systems, can not be directly applied to end-to-end deep learning systems. We propose a three-player adversarial game between a convex generator, a multi-class classifier network, and a real/fake discriminator to perform oversampling in deep learning systems. The convex generator generates new samples from the minority classes as convex combinations of existing instances, aiming to fool both the discriminator as well as the classifier into misclassifying the generated samples. Consequently, the artificial samples are generated at critical locations near the peripheries of the classes. This, in turn, adjusts the classifier induced boundaries in a way which is more likely to reduce misclassification from the minority classes. Extensive experiments on multiple class imbalanced image datasets establish the efficacy of our proposal. |
| Tasks | |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09730v2 |
| http://arxiv.org/pdf/1903.09730v2.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-minority-oversampling |
| Repo | https://github.com/SankhaSubhra/GAMO |
| Framework | none |
Regularized Learning for Domain Adaptation under Label Shifts
| Title | Regularized Learning for Domain Adaptation under Label Shifts |
| Authors | Kamyar Azizzadenesheli, Anqi Liu, Fanny Yang, Animashree Anandkumar |
| Abstract | We propose Regularized Learning under Label shifts (RLLS), a principled and a practical domain-adaptation algorithm to correct for shifts in the label distribution between a source and a target domain. We first estimate importance weights using labeled source data and unlabeled target data, and then train a classifier on the weighted source samples. We derive a generalization bound for the classifier on the target domain which is independent of the (ambient) data dimensions, and instead only depends on the complexity of the function class. To the best of our knowledge, this is the first generalization bound for the label-shift problem where the labels in the target domain are not available. Based on this bound, we propose a regularized estimator for the small-sample regime which accounts for the uncertainty in the estimated weights. Experiments on the CIFAR-10 and MNIST datasets show that RLLS improves classification accuracy, especially in the low sample and large-shift regimes, compared to previous methods. |
| Tasks | Domain Adaptation |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09734v1 |
| http://arxiv.org/pdf/1903.09734v1.pdf | |
| PWC | https://paperswithcode.com/paper/regularized-learning-for-domain-adaptation-1 |
| Repo | https://github.com/Angela0428/labelshift |
| Framework | pytorch |
Training Deep SLAM on Single Frames
| Title | Training Deep SLAM on Single Frames |
| Authors | Igor Slinko, Anna Vorontsova, Dmitry Zhukov, Olga Barinova, Anton Konushin |
| Abstract | Learning-based visual odometry and SLAM methods demonstrate a steady improvement over past years. However, collecting ground truth poses to train these methods is difficult and expensive. This could be resolved by training in an unsupervised mode, but there is still a large gap between performance of unsupervised and supervised methods. In this work, we focus on generating synthetic data for deep learning-based visual odometry and SLAM methods that take optical flow as an input. We produce training data in a form of optical flow that corresponds to arbitrary camera movement between a real frame and a virtual frame. For synthesizing data we use depth maps either produced by a depth sensor or estimated from stereo pair. We train visual odometry model on synthetic data and do not use ground truth poses hence this model can be considered unsupervised. Also it can be classified as monocular as we do not use depth maps on inference. We also propose a simple way to convert any visual odometry model into a SLAM method based on frame matching and graph optimization. We demonstrate that both the synthetically-trained visual odometry model and the proposed SLAM method build upon this model yields state-of-the-art results among unsupervised methods on KITTI dataset and shows promising results on a challenging EuRoC dataset. |
| Tasks | Optical Flow Estimation, Visual Odometry |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05405v1 |
| https://arxiv.org/pdf/1912.05405v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-deep-slam-on-single-frames |
| Repo | https://github.com/saic-vul/odometry |
| Framework | none |
MadMiner: Machine learning-based inference for particle physics
| Title | MadMiner: Machine learning-based inference for particle physics |
| Authors | Johann Brehmer, Felix Kling, Irina Espejo, Kyle Cranmer |
| Abstract | Precision measurements at the LHC often require analyzing high-dimensional event data for subtle kinematic signatures, which is challenging for established analysis methods. Recently, a powerful family of multivariate inference techniques that leverage both matrix element information and machine learning has been developed. This approach neither requires the reduction of high-dimensional data to summary statistics nor any simplifications to the underlying physics or detector response. In this paper we introduce MadMiner, a Python module that streamlines the steps involved in this procedure. Wrapping around MadGraph5_aMC and Pythia 8, it supports almost any physics process and model. To aid phenomenological studies, the tool also wraps around Delphes 3, though it is extendable to a full Geant4-based detector simulation. We demonstrate the use of MadMiner in an example analysis of dimension-six operators in ttH production, finding that the new techniques substantially increase the sensitivity to new physics. |
| Tasks | |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10621v2 |
| https://arxiv.org/pdf/1907.10621v2.pdf | |
| PWC | https://paperswithcode.com/paper/madminer-machine-learning-based-inference-for |
| Repo | https://github.com/diana-hep/madminer |
| Framework | pytorch |
Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images
| Title | Exploiting GAN Internal Capacity for High-Quality Reconstruction of Natural Images |
| Authors | Marcos Pividori, Guillermo L. Grinblat, Lucas C. Uzal |
| Abstract | Generative Adversarial Networks (GAN) have demonstrated impressive results in modeling the distribution of natural images, learning latent representations that capture semantic variations in an unsupervised basis. Beyond the generation of novel samples, it is of special interest to exploit the ability of the GAN generator to model the natural image manifold and hence generate credible changes when manipulating images. However, this line of work is conditioned by the quality of the reconstruction. Until now, only inversion to the latent space has been considered, we propose to exploit the representation in intermediate layers of the generator, and we show that this leads to increased capacity. In particular, we observe that the representation after the first dense layer, present in all state-of-the-art GAN models, is expressive enough to represent natural images with high visual fidelity. It is possible to interpolate around these images obtaining a sequence of new plausible synthetic images that cannot be generated from the latent space. Finally, as an example of potential applications that arise from this inversion mechanism, we show preliminary results in exploiting the learned representation in the attention map of the generator to obtain an unsupervised segmentation of natural images. |
| Tasks | |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1911.05630v1 |
| https://arxiv.org/pdf/1911.05630v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-gan-internal-capacity-for-high |
| Repo | https://github.com/CIFASIS/exploiting-gan-internal-capacity |
| Framework | tf |
Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best
| Title | Efficient Evolutionary Methods for Game Agent Optimisation: Model-Based is Best |
| Authors | Simon M. Lucas, Jialin Liu, Ivan Bravi, Raluca D. Gaina, John Woodward, Vanessa Volz, Diego Perez-Liebana |
| Abstract | This paper introduces a simple and fast variant of Planet Wars as a test-bed for statistical planning based Game AI agents, and for noisy hyper-parameter optimisation. Planet Wars is a real-time strategy game with simple rules but complex game-play. The variant introduced in this paper is designed for speed to enable efficient experimentation, and also for a fixed action space to enable practical inter-operability with General Video Game AI agents. If we treat the game as a win-loss game (which is standard), then this leads to challenging noisy optimisation problems both in tuning agents to play the game, and in tuning game parameters. Here we focus on the problem of tuning an agent, and report results using the recently developed N-Tuple Bandit Evolutionary Algorithm and a number of other optimisers, including Sequential Model-based Algorithm Configuration (SMAC). Results indicate that the N-Tuple Bandit Evolutionary offers competitive performance as well as insight into the effects of combinations of parameter choices. |
| Tasks | |
| Published | 2019-01-03 |
| URL | http://arxiv.org/abs/1901.00723v1 |
| http://arxiv.org/pdf/1901.00723v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-evolutionary-methods-for-game-agent |
| Repo | https://github.com/SimonLucas/ntbea |
| Framework | none |
