Paper Group ANR 1070
A Geometric Perspective on Optimal Representations for Reinforcement Learning. The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents. Marginally-calibrated deep distributional regression. Meta-Weighted Gaussian Process Experts for Personalized Forecasting of AD Cognitive Changes. Classification of Two-channel Sign …
A Geometric Perspective on Optimal Representations for Reinforcement Learning
| Title | A Geometric Perspective on Optimal Representations for Reinforcement Learning |
| Authors | Marc G. Bellemare, Will Dabney, Robert Dadashi, Adrien Ali Taiga, Pablo Samuel Castro, Nicolas Le Roux, Dale Schuurmans, Tor Lattimore, Clare Lyle |
| Abstract | We propose a new perspective on representation learning in reinforcement learning based on geometric properties of the space of value functions. We leverage this perspective to provide formal evidence regarding the usefulness of value functions as auxiliary tasks. Our formulation considers adapting the representation to minimize the (linear) approximation of the value function of all stationary policies for a given environment. We show that this optimization reduces to making accurate predictions regarding a special class of value functions which we call adversarial value functions (AVFs). We demonstrate that using value functions as auxiliary tasks corresponds to an expected-error relaxation of our formulation, with AVFs a natural candidate, and identify a close relationship with proto-value functions (Mahadevan, 2005). We highlight characteristics of AVFs and their usefulness as auxiliary tasks in a series of experiments on the four-room domain. |
| Tasks | Representation Learning |
| Published | 2019-01-31 |
| URL | https://arxiv.org/abs/1901.11530v2 |
| https://arxiv.org/pdf/1901.11530v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-geometric-perspective-on-optimal |
| Repo | |
| Framework | |
The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents
| Title | The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents |
| Authors | Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, Jason Weston |
| Abstract | We introduce dodecaDialogue: a set of 12 tasks that measures if a conversational agent can communicate engagingly with personality and empathy, ask questions, answer questions by utilizing knowledge resources, discuss topics and situations, and perceive and converse about images. By multi-tasking on such a broad large-scale set of data, we hope to both move towards and measure progress in producing a single unified agent that can perceive, reason and converse with humans in an open-domain setting. We show that such multi-tasking improves over a BERT pre-trained baseline, largely due to multi-tasking with very large dialogue datasets in a similar domain, and that the multi-tasking in general provides gains to both text and image-based tasks using several metrics in both the fine-tune and task transfer settings. We obtain state-of-the-art results on many of the tasks, providing a strong baseline for this challenge. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03768v1 |
| https://arxiv.org/pdf/1911.03768v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-dialogue-dodecathlon-open-domain |
| Repo | |
| Framework | |
Marginally-calibrated deep distributional regression
| Title | Marginally-calibrated deep distributional regression |
| Authors | Nadja Klein, David J. Nott, Michael Stanley Smith |
| Abstract | Deep neural network (DNN) regression models are widely used in applications requiring state-of-the-art predictive accuracy. However, until recently there has been little work on accurate uncertainty quantification for predictions from such models. We add to this literature by outlining an approach to constructing predictive distributions that are `marginally calibrated’. This is where the long run average of the predictive distributions of the response variable matches the observed empirical margin. Our approach considers a DNN regression with a conditionally Gaussian prior for the final layer weights, from which an implicit copula process on the feature space is extracted. This copula process is combined with a non-parametrically estimated marginal distribution for the response. The end result is a scalable distributional DNN regression method with marginally calibrated predictions, and our work complements existing methods for probability calibration. The approach is first illustrated using two applications of dense layer feed-forward neural networks. However, our main motivating applications are in likelihood-free inference, where distributional deep regression is used to estimate marginal posterior distributions. In two complex ecological time series examples we employ the implicit copulas of convolutional networks, and show that marginal calibration results in improved uncertainty quantification. Our approach also avoids the need for manual specification of summary statistics, a requirement that is burdensome for users and typical of competing likelihood-free inference methods. | |
| Tasks | Calibration, Time Series |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1908.09482v1 |
| https://arxiv.org/pdf/1908.09482v1.pdf | |
| PWC | https://paperswithcode.com/paper/marginally-calibrated-deep-distributional |
| Repo | |
| Framework | |
Meta-Weighted Gaussian Process Experts for Personalized Forecasting of AD Cognitive Changes
| Title | Meta-Weighted Gaussian Process Experts for Personalized Forecasting of AD Cognitive Changes |
| Authors | Ognjen Rudovic, Yuria Utsumi, Ricardo Guerrero, Kelly Peterson, Daniel Rueckert, Rosalind W. Picard |
| Abstract | We introduce a novel personalized Gaussian Process Experts (pGPE) model for predicting per-subject ADAS-Cog13 cognitive scores – a significant predictor of Alzheimer’s Disease (AD) in the cognitive domain – over the future 6, 12, 18, and 24 months. We start by training a population-level model using multi-modal data from previously seen subjects using a base Gaussian Process (GP) regression. Then, we personalize this model by adapting the base GP sequentially over time to a new (target) subject using domain adaptive GPs, and also by training subject-specific GP. While we show that these models achieve improved performance when selectively applied to the forecasting task (one performs better than the other on different subjects/visits), the average performance per model is suboptimal. To this end, we used the notion of meta learning in the proposed pGPE to design a regression-based weighting of these expert models, where the expert weights are optimized for each subject and his/her future visit. The results on a cohort of subjects from the ADNI dataset show that this newly introduced personalized weighting of the expert models leads to large improvements in accurately forecasting future ADAS-Cog13 scores and their fine-grained changes associated with the AD progression. This approach has potential to help identify at-risk patients early and improve the construction of clinical trials for AD. |
| Tasks | Meta-Learning |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09370v1 |
| http://arxiv.org/pdf/1904.09370v1.pdf | |
| PWC | https://paperswithcode.com/paper/190409370 |
| Repo | |
| Framework | |
Classification of Two-channel Signals by Means of Genetic Programming
| Title | Classification of Two-channel Signals by Means of Genetic Programming |
| Authors | Daniel Rivero, Enrique Fernandez-Blanco, Julian Dorado, Alejandro Pazos |
| Abstract | Traditionally, signal classification is a process in which previous knowledge of the signals is needed. Human experts decide which features are extracted from the signals, and used as inputs to the classification system. This requirement can make significant unknown information of the signal be missed by the experts and not be included in the features. This paper proposes a new method that automatically analyses the signals and extracts the features without any human participation. Therefore, there is no need for previous knowledge about the signals to be classified. The proposed method is based on Genetic Programming and, in order to test this method, it has been applied to a well-known EEG database related to epilepsy, a disease suffered by millions of people. As the results section shows, high accuracies in classification are obtained |
| Tasks | EEG |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.05027v1 |
| http://arxiv.org/pdf/1904.05027v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-two-channel-signals-by |
| Repo | |
| Framework | |
Detecting organized eCommerce fraud using scalable categorical clustering
| Title | Detecting organized eCommerce fraud using scalable categorical clustering |
| Authors | Samuel Marchal, Sebastian Szyller |
| Abstract | Online retail, eCommerce, frequently falls victim to fraud conducted by malicious customers (fraudsters) who obtain goods or services through deception. Fraud coordinated by groups of professional fraudsters that place several fraudulent orders to maximize their gain is referred to as organized fraud. Existing approaches to fraud detection typically analyze orders in isolation and they are not effective at identifying groups of fraudulent orders linked to organized fraud. These also wrongly identify many legitimate orders as fraud, which hinders their usage for automated fraud cancellation. We introduce a novel solution to detect organized fraud by analyzing orders in bulk. Our approach is based on clustering and aims to group together fraudulent orders placed by the same group of fraudsters. It selectively uses two existing techniques, agglomerative clustering and sampling to recursively group orders into small clusters in a reasonable amount of time. We assess our clustering technique on real-world orders placed on the Zalando website, the largest online apparel retailer in Europe1. Our clustering processes 100,000s of orders in a few hours and groups 35-45% of fraudulent orders together. We propose a simple technique built on top of our clustering that detects 26.2% of fraud while raising false alarms for only 0.1% of legitimate orders. |
| Tasks | Fraud Detection |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04514v1 |
| https://arxiv.org/pdf/1910.04514v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-organized-ecommerce-fraud-using |
| Repo | |
| Framework | |
Lipschitz Bandit Optimization with Improved Efficiency
| Title | Lipschitz Bandit Optimization with Improved Efficiency |
| Authors | Xu Zhu, David B. Dunson |
| Abstract | We consider the Lipschitz bandit optimization problem with an emphasis on practical efficiency. Although there is rich literature on regret analysis of this type of problem, e.g., [Kleinberg et al. 2008, Bubeck et al. 2011, Slivkins 2014], their proposed algorithms suffer from serious practical problems including extreme time complexity and dependence on oracle implementations. With this motivation, we propose a novel algorithm with an Upper Confidence Bound (UCB) exploration, namely Tree UCB-Hoeffding, using adaptive partitions. Our partitioning scheme is easy to implement and does not require any oracle settings. With a tree-based search strategy, the total computational cost can be improved to $\mathcal{O}(T\log T)$ for the first $T$ iterations. In addition, our algorithm achieves the regret lower bound up to a logarithmic factor. |
| Tasks | |
| Published | 2019-04-25 |
| URL | https://arxiv.org/abs/1904.11131v2 |
| https://arxiv.org/pdf/1904.11131v2.pdf | |
| PWC | https://paperswithcode.com/paper/lipschitz-bandit-optimization-with-improved |
| Repo | |
| Framework | |
Artificial intelligence-based process for metal scrap sorting
| Title | Artificial intelligence-based process for metal scrap sorting |
| Authors | Maximilian Auer, Kai Osswald, Raphael Volz, Joerg Woidasky |
| Abstract | Machine learning offers remarkable benefits for improving workplaces and working conditions amongst others in the recycling industry. Here e.g. hand-sorting of medium value scrap is labor intensive and requires experienced and skilled workers. On the one hand, they have to be highly concentrated for making proper readings and analyses of the material, but on the other hand, this work is monotonous. Therefore, a machine learning approach is proposed for a quick and reliable automated identification of alloys in the recycling industry, while the mere scrap handling is regarded to be left in the hands of the workers. To this end, a set of twelve tool and high-speed steels from the field were selected to be identified by their spectrum induced by electric arcs. For data acquisition, the optical emission spectrometer Thorlabs CCS 100 was used. Spectra have been post-processed to be fed into the supervised machine learning algorithm. The development of the machine learning software is conducted according to the steps of the VDI 2221 standard method. For programming Python 3 as well as the python-library sklearn were used. By systematic parameter variation, the appropriate machine learning algorithm was selected and validated. Subsequent validation steps showed that the automated identification process using a machine learning approach and the optical emission spectrometry is applicable, reaching a maximum F1 score of 96.9 %. This performance is as good as the performance of a highly trained worker using visual grinding spark identification. The tests were based on a self-generated set of 600 spectra per single alloy (7,200 spectra in total) which were produced using an industry workshop device. |
| Tasks | |
| Published | 2019-03-22 |
| URL | http://arxiv.org/abs/1903.09415v1 |
| http://arxiv.org/pdf/1903.09415v1.pdf | |
| PWC | https://paperswithcode.com/paper/artificial-intelligence-based-process-for |
| Repo | |
| Framework | |
An Optimized PatchMatch for Multi-scale and Multi-feature Label Fusion
| Title | An Optimized PatchMatch for Multi-scale and Multi-feature Label Fusion |
| Authors | Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis, José V. Manjón, D. Louis Collins, Pierrick Coupé, Alzheimer’s Disease Neuroimaging Initiative |
| Abstract | Automatic segmentation methods are important tools for quantitative analysis of Magnetic Resonance Images (MRI). Recently, patch-based label fusion approaches have demonstrated state-of-the-art segmentation accuracy. In this paper, we introduce a new patch-based label fusion framework to perform segmentation of anatomical structures. The proposed approach uses an Optimized PAtchMatch Label fusion (OPAL) strategy that drastically reduces the computation time required for the search of similar patches. The reduced computation time of OPAL opens the way for new strategies and facilitates processing on large databases. In this paper, we investigate new perspectives offered by OPAL, by introducing a new multi-scale and multi-feature framework. During our validation on hippocampus segmentation we use two datasets: young adults in the ICBM cohort and elderly adults in the EADC-ADNI dataset. For both, OPAL is compared to state-of-the-art methods. Results show that OPAL obtained the highest median Dice coefficient (89.9% for ICBM and 90.1% for EADC-ADNI). Moreover, in both cases, OPAL produced a segmentation accuracy similar to inter-expert variability. On the EADC-ADNI dataset, we compare the hippocampal volumes obtained by manual and automatic segmentation. The volumes appear to be highly correlated that enables to perform more accurate separation of pathological populations. |
| Tasks | |
| Published | 2019-03-17 |
| URL | http://arxiv.org/abs/1903.07165v1 |
| http://arxiv.org/pdf/1903.07165v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-optimized-patchmatch-for-multi-scale-and |
| Repo | |
| Framework | |
On the validity of memristor modeling in the neural network literature
| Title | On the validity of memristor modeling in the neural network literature |
| Authors | Y. V. Pershin, M. Di Ventra |
| Abstract | An analysis of the literature shows that there are two types of non-memristive models that have been widely used in the modeling of so-called “memristive” neural networks. Here, we demonstrate that such models have nothing in common with the concept of memristive elements: they describe either non-linear resistors or certain bi-state systems, which all are devices without memory. Therefore, the results presented in a significant number of publications are at least questionable, if not completely irrelevant to the actual field of memristive neural networks. |
| Tasks | |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08839v1 |
| http://arxiv.org/pdf/1904.08839v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-validity-of-memristor-modeling-in-the |
| Repo | |
| Framework | |
Adversarial Reinforcement Learning under Partial Observability in Software-Defined Networking
| Title | Adversarial Reinforcement Learning under Partial Observability in Software-Defined Networking |
| Authors | Yi Han, David Hubczenko, Paul Montague, Olivier De Vel, Tamas Abraham, Benjamin I. P. Rubinstein, Christopher Leckie, Tansu Alpcan, Sarah Erfani |
| Abstract | Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised setting. Accordingly focus has remained with computer vision, and full observability. This paper focuses on reinforcement learning in the context of autonomous defence in Software-Defined Networking (SDN). We demonstrate that causative attacks—attacks that target the training process—can poison RL agents even if the attacker only has partial observability of the environment. In addition, we propose an inversion defence method that aims to apply the opposite perturbation to that which an attacker might use to generate their adversarial samples. Our experimental results illustrate that the countermeasure can effectively reduce the impact of the causative attack, while not significantly affecting the training process in non-attack scenarios. |
| Tasks | |
| Published | 2019-02-25 |
| URL | https://arxiv.org/abs/1902.09062v2 |
| https://arxiv.org/pdf/1902.09062v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-reinforcement-learning-under |
| Repo | |
| Framework | |
Character-Centric Storytelling
| Title | Character-Centric Storytelling |
| Authors | Aditya Surikuchi, Jorma Laaksonen |
| Abstract | Sequential vision-to-language or visual storytelling has recently been one of the areas of focus in computer vision and language modeling domains. Though existing models generate narratives that read subjectively well, there could be cases when these models miss out on generating stories that account and address all prospective human and animal characters in the image sequences. Considering this scenario, we propose a model that implicitly learns relationships between provided characters and thereby generates stories with respective characters in scope. We use the VIST dataset for this purpose and report numerous statistics on the dataset. Eventually, we describe the model, explain the experiment and discuss our current status and future work. |
| Tasks | Language Modelling, Visual Storytelling |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07863v3 |
| https://arxiv.org/pdf/1909.07863v3.pdf | |
| PWC | https://paperswithcode.com/paper/character-centric-storytelling |
| Repo | |
| Framework | |
Sequence embeddings help to identify fraudulent cases in healthcare insurance
| Title | Sequence embeddings help to identify fraudulent cases in healthcare insurance |
| Authors | I. Fursov, A. Zaytsev, R. Khasyanov, M. Spindler, E. Burnaev |
| Abstract | Fraud causes substantial costs and losses for companies and clients in the finance and insurance industries. Examples are fraudulent credit card transactions or fraudulent claims. It has been estimated that roughly $10$ percent of the insurance industry’s incurred losses and loss adjustment expenses each year stem from fraudulent claims. The rise and proliferation of digitization in finance and insurance have lead to big data sets, consisting in particular of text data, which can be used for fraud detection. In this paper, we propose architectures for text embeddings via deep learning, which help to improve the detection of fraudulent claims compared to other machine learning methods. We illustrate our methods using a data set from a large international health insurance company. The empirical results show that our approach outperforms other state-of-the-art methods and can help make the claims management process more efficient. As (unstructured) text data become increasingly available to economists and econometricians, our proposed methods will be valuable for many similar applications, particularly when variables have a large number of categories as is typical for example of the International Classification of Disease (ICD) codes in health economics and health services. |
| Tasks | Fraud Detection |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.03072v1 |
| https://arxiv.org/pdf/1910.03072v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequence-embeddings-help-to-identify |
| Repo | |
| Framework | |
Embodied Language Grounding with Implicit 3D Visual Feature Representations
| Title | Embodied Language Grounding with Implicit 3D Visual Feature Representations |
| Authors | Mihir Prabhudesai, Hsiao-Yu Fish Tung, Syed Ashar Javed, Maximilian Sieb, Adam W. Harley, Katerina Fragkiadaki |
| Abstract | Consider the utterance “the tomato is to the left of the pot.” Humans can answer numerous questions about the situation described, as well as reason through counterfactuals and alternatives, such as, “is the pot larger than the tomato ?", “can we move to a viewpoint from which the tomato is completely hidden behind the pot ?", “can we have an object that is both to the left of the tomato and to the right of the pot ?", “would the tomato fit inside the pot ?", and so on. Such reasoning capability remains elusive from current computational models of language understanding. To link language processing with spatial reasoning, we propose associating natural language utterances to a mental workspace of their meaning, encoded as 3-dimensional visual feature representations of the world scenes they describe. We learn such 3-dimensional visual representations—we call them visual imaginations— by predicting images a mobile agent sees while moving around in the 3D world. The input image streams the agent collects are unprojected into egomotion-stable 3D scene feature maps of the scene, and projected from novel viewpoints to match the observed RGB image views in an end-to-end differentiable manner. We then train modular neural models to generate such 3D feature representations given language utterances, to localize the objects an utterance mentions in the 3D feature representation inferred from an image, and to predict the desired 3D object locations given a manipulation instruction. We empirically show the proposed models outperform by a large margin existing 2D models in spatial reasoning, referential object detection and instruction following, and generalize better across camera viewpoints and object arrangements. |
| Tasks | Object Detection |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.01210v2 |
| https://arxiv.org/pdf/1910.01210v2.pdf | |
| PWC | https://paperswithcode.com/paper/embodied-language-grounding-with-implicit-3d |
| Repo | |
| Framework | |
User profiles matching for different social networks based on faces embeddings
| Title | User profiles matching for different social networks based on faces embeddings |
| Authors | Timur Sokhin, Nikolay Butakov, Denis Nasonov |
| Abstract | It is common practice nowadays to use multiple social networks for different social roles. Although this, these networks assume differences in content type, communications and style of speech. If we intend to understand human behaviour as a key-feature for recommender systems, banking risk assessments or sociological researches, this is better to achieve using a combination of the data from different social media. In this paper, we propose a new approach for user profiles matching across social media based on embeddings of publicly available users’ face photos and conduct an experimental study of its efficiency. Our approach is stable to changes in content and style for certain social media. |
| Tasks | Recommendation Systems |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06081v1 |
| https://arxiv.org/pdf/1905.06081v1.pdf | |
| PWC | https://paperswithcode.com/paper/user-profiles-matching-for-different-social |
| Repo | |
| Framework | |
