Paper Group ANR 466
Sparse Black-box Video Attack with Reinforcement Learning. Differentiable Likelihoods for Fast Inversion of ‘Likelihood-Free’ Dynamical Systems. Adaptive Large Neighborhood Search for Circle Bin Packing Problem. On The Reasons Behind Decisions. Enabling Viewpoint Learning through Dynamic Label Generation. Aggregation of Multiple Knockoffs. Large-Sc …
Sparse Black-box Video Attack with Reinforcement Learning
| Title | Sparse Black-box Video Attack with Reinforcement Learning |
| Authors | Huanqian Yan, Xingxing Wei, Bo Li |
| Abstract | Black-box adversarial attacks on video recognition models have been explored. Considering the temporal interactions between frames, a few methods try to select some key frames, and then perform attacks on them. Unfortunately, their selecting strategy is independent with the attacking step, resulting in the limited performance. Instead, we argue the frame selection phase is closely relevant with the attacking phase. The key frames should be adjusted according to the attacking results. For that, we formulate the black-box video attacks into Reinforcement Learning (RL) framework. Specifically, the environment in RL is set as the threat model, and the agent in RL plays the role of frame selecting. By continuously querying the threat models and receiving the attacking feedback, the agent gradually adjusts its frame selection strategy and adversarial perturbations become smaller and smaller. A series of experiments demonstrate that our method can significantly reduce the adversarial perturbations with efficient query times. |
| Tasks | Video Recognition |
| Published | 2020-01-11 |
| URL | https://arxiv.org/abs/2001.03754v2 |
| https://arxiv.org/pdf/2001.03754v2.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-black-box-video-attack-with |
| Repo | |
| Framework | |
Differentiable Likelihoods for Fast Inversion of ‘Likelihood-Free’ Dynamical Systems
| Title | Differentiable Likelihoods for Fast Inversion of ‘Likelihood-Free’ Dynamical Systems |
| Authors | Hans Kersting, Nicholas Krämer, Martin Schiegg, Christian Daniel, Michael Tiemann, Philipp Hennig |
| Abstract | Likelihood-free (a.k.a. simulation-based) inference problems are inverse problems with expensive, or intractable, forward models. ODE inverse problems are commonly treated as likelihood-free, as their forward map has to be numerically approximated by an ODE solver. This, however, is not a fundamental constraint but just a lack of functionality in classic ODE solvers, which do not return a likelihood but a point estimate. To address this shortcoming, we employ Gaussian ODE filtering (a probabilistic numerical method for ODEs) to construct a local Gaussian approximation to the likelihood. This approximation yields tractable estimators for the gradient and Hessian of the (log-)likelihood. Insertion of these estimators into existing gradient-based optimization and sampling methods engenders new solvers for ODE inverse problems. We demonstrate that these methods outperform standard likelihood-free approaches on three benchmark-systems. |
| Tasks | |
| Published | 2020-02-21 |
| URL | https://arxiv.org/abs/2002.09301v1 |
| https://arxiv.org/pdf/2002.09301v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-likelihoods-for-fast-inversion |
| Repo | |
| Framework | |
Adaptive Large Neighborhood Search for Circle Bin Packing Problem
| Title | Adaptive Large Neighborhood Search for Circle Bin Packing Problem |
| Authors | Kun He, Kevin Tole, Fei Ni, Yong Yuan, Linyun Liao |
| Abstract | We address a new variant of packing problem called the circle bin packing problem (CBPP), which is to find a dense packing of circle items to multiple square bins so as to minimize the number of used bins. To this end, we propose an adaptive large neighborhood search (ALNS) algorithm, which uses our Greedy Algorithm with Corner Occupying Action (GACOA) to construct an initial layout. The greedy solution is usually in a local optimum trap, and ALNS enables multiple neighborhood search that depends on the stochastic annealing schedule to avoid getting stuck in local minimum traps. Specifically, ALNS perturbs the current layout to jump out of a local optimum by iteratively reassigns some circles and accepts the new layout with some probability during the search. The acceptance probability is adjusted adaptively using simulated annealing that fine-tunes the search direction in order to reach the global optimum. We benchmark computational results against GACOA in heterogeneous instances. ALNS always outperforms GACOA in improving the objective function, and in several cases, there is a significant reduction on the number of bins used in the packing. |
| Tasks | |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.07709v1 |
| https://arxiv.org/pdf/2001.07709v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-large-neighborhood-search-for-circle |
| Repo | |
| Framework | |
On The Reasons Behind Decisions
| Title | On The Reasons Behind Decisions |
| Authors | Adnan Darwiche, Auguste Hirth |
| Abstract | Recent work has shown that some common machine learning classifiers can be compiled into Boolean circuits that have the same input-output behavior. We present a theory for unveiling the reasons behind the decisions made by Boolean classifiers and study some of its theoretical and practical implications. We define notions such as sufficient, necessary and complete reasons behind decisions, in addition to classifier and decision bias. We show how these notions can be used to evaluate counterfactual statements such as “a decision will stick even if … because … .” We present efficient algorithms for computing these notions, which are based on new advances on tractable Boolean circuits, and illustrate them using a case study. |
| Tasks | |
| Published | 2020-02-21 |
| URL | https://arxiv.org/abs/2002.09284v1 |
| https://arxiv.org/pdf/2002.09284v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-reasons-behind-decisions |
| Repo | |
| Framework | |
Enabling Viewpoint Learning through Dynamic Label Generation
| Title | Enabling Viewpoint Learning through Dynamic Label Generation |
| Authors | Michael Schelling, Pedro Hermosilla, Pere-Pau Vazquez, Timo Ropinski |
| Abstract | Optimal viewpoint prediction is an essential task in many computer graphicsapplications. Unfortunately, common viewpoint qualities suffer from majordrawbacks: dependency on clean surface meshes, which are not alwaysavailable, insensitivity to upright orientation, and the lack of closed-formexpressions, which requires a costly sampling process involving rendering.We overcome these limitations through a 3D deep learning approach, whichsolely exploits vertex coordinate information to predict optimal viewpointsunder upright orientation, while reflecting both informational content andhuman preference analysis. To enable this approach we propose a dynamiclabel generation strategy, which resolves inherent label ambiguities dur-ing training. In contrast to previous viewpoint prediction methods, whichevaluate many rendered views, we directly learn on the 3D mesh, and arethus independent from rendering. Furthermore, by exploiting unstructuredlearning, we are independent of mesh discretization. We show how the pro-posed technology enables learned prediction from model to viewpoints fordifferent object categories and viewpoint qualities. Additionally, we showthat prediction times are reduced from several minutes to a fraction of asecond, as compared to viewpoint quality evaluation. We will release thecode and training data, which will to our knowledge be the biggest viewpointquality dataset available. |
| Tasks | |
| Published | 2020-03-10 |
| URL | https://arxiv.org/abs/2003.04651v1 |
| https://arxiv.org/pdf/2003.04651v1.pdf | |
| PWC | https://paperswithcode.com/paper/enabling-viewpoint-learning-through-dynamic |
| Repo | |
| Framework | |
Aggregation of Multiple Knockoffs
| Title | Aggregation of Multiple Knockoffs |
| Authors | Binh T. Nguyen, Jérôme-Alexis Chevalier, Bertrand Thirion, Sylvain Arlot |
| Abstract | We develop an extension of the Knockoff Inference procedure, introduced by Barber and Candes (2015). This new method, called Aggregation of Multiple Knockoffs (AKO), addresses the instability inherent to the random nature of Knockoff-based inference. Specifically, AKO improves both the stability and power compared with the original Knockoff algorithm while still maintaining guarantees for False Discovery Rate control. We provide a new inference procedure, prove its core properties, and demonstrate its benefits in a set of experiments on synthetic and real datasets. |
| Tasks | |
| Published | 2020-02-21 |
| URL | https://arxiv.org/abs/2002.09269v1 |
| https://arxiv.org/pdf/2002.09269v1.pdf | |
| PWC | https://paperswithcode.com/paper/aggregation-of-multiple-knockoffs |
| Repo | |
| Framework | |
Large-Scale Evaluation of Keyphrase Extraction Models
| Title | Large-Scale Evaluation of Keyphrase Extraction Models |
| Authors | Ygor Gallina, Florian Boudin, Béatrice Daille |
| Abstract | Keyphrase extraction models are usually evaluated under different, not directly comparable, experimental setups. As a result, it remains unclear how well proposed models actually perform, and how they compare to each other. In this work, we address this issue by presenting a systematic large-scale analysis of state-of-the-art keyphrase extraction models involving multiple benchmark datasets from various sources and domains. Our main results reveal that state-of-the-art models are in fact still challenged by simple baselines on some datasets. We also present new insights about the impact of using author- or reader-assigned keyphrases as a proxy for gold standard, and give recommendations for strong baselines and reliable benchmark datasets. |
| Tasks | |
| Published | 2020-03-10 |
| URL | https://arxiv.org/abs/2003.04628v1 |
| https://arxiv.org/pdf/2003.04628v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-evaluation-of-keyphrase |
| Repo | |
| Framework | |
Age-Conditioned Synthesis of Pediatric Computed Tomography with Auxiliary Classifier Generative Adversarial Networks
| Title | Age-Conditioned Synthesis of Pediatric Computed Tomography with Auxiliary Classifier Generative Adversarial Networks |
| Authors | Chi Nok Enoch Kan, Najibakram Maheenaboobacker, Dong Hye Ye |
| Abstract | Deep learning is a popular and powerful tool in computed tomography (CT) image processing such as organ segmentation, but its requirement of large training datasets remains a challenge. Even though there is a large anatomical variability for children during their growth, the training datasets for pediatric CT scans are especially hard to obtain due to risks of radiation to children. In this paper, we propose a method to conditionally synthesize realistic pediatric CT images using a new auxiliary classifier generative adversarial network (ACGAN) architecture by taking age information into account. The proposed network generated age-conditioned high-resolution CT images to enrich pediatric training datasets. |
| Tasks | Computed Tomography (CT) |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2002.00011v1 |
| https://arxiv.org/pdf/2002.00011v1.pdf | |
| PWC | https://paperswithcode.com/paper/age-conditioned-synthesis-of-pediatric |
| Repo | |
| Framework | |
Autonomous Planning Based on Spatial Concepts to Tidy Up Home Environments with Service Robots
| Title | Autonomous Planning Based on Spatial Concepts to Tidy Up Home Environments with Service Robots |
| Authors | Akira Taniguchi, Shota Isobe, Lotfi El Hafi, Yoshinobu Hagiwara, Tadahiro Taniguchi |
| Abstract | Tidy-up tasks by service robots in home environments are challenging in the application of robotics because they involve various interactions with the environment. In particular, robots are required not only to grasp, move, and release various home objects, but also plan the order and positions where to put them away. In this paper, we propose a novel planning method that can efficiently estimate the order and positions of the objects to be tidied up based on the learning of the parameters of a probabilistic generative model. The model allows the robot to learn the distributions of co-occurrence probability of objects and places to tidy up by using multimodal sensor information collected in a tidied environment. Additionally, we develop an autonomous robotic system to perform the tidy-up operation. We evaluate the effectiveness of the proposed method in an experimental simulation that reproduces the conditions of the Tidy Up Here task of the World Robot Summit international robotics competition. The simulation results showed that the proposed method enables the robot to successively tidy up several objects and achieves the best task score compared to baseline tidy-up methods. |
| Tasks | |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03671v1 |
| https://arxiv.org/pdf/2002.03671v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-planning-based-on-spatial-concepts |
| Repo | |
| Framework | |
Offline Contextual Bayesian Optimization for Nuclear Fusion
| Title | Offline Contextual Bayesian Optimization for Nuclear Fusion |
| Authors | Youngseog Chung, Ian Char, Willie Neiswanger, Kirthevasan Kandasamy, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider |
| Abstract | Nuclear fusion is regarded as the energy of the future since it presents the possibility of unlimited clean energy. One obstacle in utilizing fusion as a feasible energy source is the stability of the reaction. Ideally, one would have a controller for the reactor that makes actions in response to the current state of the plasma in order to prolong the reaction as long as possible. In this work, we make preliminary steps to learning such a controller. Since learning on a real world reactor is infeasible, we tackle this problem by attempting to learn optimal controls offline via a simulator, where the state of the plasma can be explicitly set. In particular, we introduce a theoretically grounded Bayesian optimization algorithm that recommends a state and action pair to evaluate at every iteration and show that this results in more efficient use of the simulator. |
| Tasks | |
| Published | 2020-01-06 |
| URL | https://arxiv.org/abs/2001.01793v1 |
| https://arxiv.org/pdf/2001.01793v1.pdf | |
| PWC | https://paperswithcode.com/paper/offline-contextual-bayesian-optimization-for |
| Repo | |
| Framework | |
ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems
| Title | ConAML: Constrained Adversarial Machine Learning for Cyber-Physical Systems |
| Authors | Jiangnan Li, Jin Young Lee, Yingyuan Yang, Jinyuan Stella Sun, Kevin Tomsovic |
| Abstract | Recent research demonstrated that the superficially well-trained machine learning (ML) models are highly vulnerable to adversarial examples. As ML techniques are rapidly employed in cyber-physical systems (CPSs), the security of these applications is of concern. However, current studies on adversarial machine learning (AML) mainly focus on computer vision and related fields. The risks the adversarial examples can bring to the CPS applications have not been well investigated. In particular, due to the distributed property of data sources and the inherent physical constraints imposed by CPSs, the widely-used threat models in previous research and the state-of-the-art AML algorithms are no longer practical when applied to CPS applications. We study the vulnerabilities of ML applied in CPSs by proposing Constrained Adversarial Machine Learning (ConAML), which generates adversarial examples used as ML model input that meet the intrinsic constraints of the physical systems. We first summarize the difference between AML in CPSs and AML in existing cyber systems and propose a general threat model for ConAML. We then design a best-effort search algorithm to iteratively generate adversarial examples with linear physical constraints. As proofs of concept, we evaluate the vulnerabilities of ML models used in the electric power grid and water treatment systems. The results show that our ConAML algorithms can effectively generate adversarial examples which significantly decrease the performance of the ML models even under practical physical constraints. |
| Tasks | |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.05631v1 |
| https://arxiv.org/pdf/2003.05631v1.pdf | |
| PWC | https://paperswithcode.com/paper/conaml-constrained-adversarial-machine |
| Repo | |
| Framework | |
A tutorial on ensembles and deep learning fusion with MNIST as guiding thread: A complex heterogeneous fusion scheme reaching 10 digits error
| Title | A tutorial on ensembles and deep learning fusion with MNIST as guiding thread: A complex heterogeneous fusion scheme reaching 10 digits error |
| Authors | S. Tabik, R. F. Alvear-Sandoval, M. M. Ruiz, J. L. Sancho-Gómez, A. R. Figueiras-Vidal, F. Herrera |
| Abstract | Ensemble methods have been widely used for improving the results of the best single classification model. Indeed, a large body of works have achieved better results mainly by applying one specific ensemble method. However, very few works analyze complex fusion schemes using heterogeneous ensemble strategies. This paper is three-fold: 1) It provides a tutorial of the most popular ensemble methods, 2) analyzes the best ensembles using MNIST as guiding thread and 3) shows that complex fusion architectures based on heterogeneous ensembles can be considered as a mode of taking benefit from diversity. We introduce a complex fusion design that achieves a new record in MNIST with only 10 misclassified images. |
| Tasks | |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11486v1 |
| https://arxiv.org/pdf/2001.11486v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tutorial-on-ensembles-and-deep-learning |
| Repo | |
| Framework | |
Recent Trends in the Use of Statistical Tests for Comparing Swarm and Evolutionary Computing Algorithms: Practical Guidelines and a Critical Review
| Title | Recent Trends in the Use of Statistical Tests for Comparing Swarm and Evolutionary Computing Algorithms: Practical Guidelines and a Critical Review |
| Authors | J. Carrasco, S. García, M. M. Rueda, S. Das, F. Herrera |
| Abstract | A key aspect of the design of evolutionary and swarm intelligence algorithms is studying their performance. Statistical comparisons are also a crucial part which allows for reliable conclusions to be drawn. In the present paper we gather and examine the approaches taken from different perspectives to summarise the assumptions made by these statistical tests, the conclusions reached and the steps followed to perform them correctly. In this paper, we conduct a survey on the current trends of the proposals of statistical analyses for the comparison of algorithms of computational intelligence and include a description of the statistical background of these tests. We illustrate the use of the most common tests in the context of the Competition on single-objective real parameter optimisation of the IEEE Congress on Evolutionary Computation (CEC) 2017 and describe the main advantages and drawbacks of the use of each kind of test and put forward some recommendations concerning their use. |
| Tasks | |
| Published | 2020-02-21 |
| URL | https://arxiv.org/abs/2002.09227v1 |
| https://arxiv.org/pdf/2002.09227v1.pdf | |
| PWC | https://paperswithcode.com/paper/recent-trends-in-the-use-of-statistical-tests |
| Repo | |
| Framework | |
Brand Intelligence Analytics
| Title | Brand Intelligence Analytics |
| Authors | A. Fronzetti Colladon, F. Grippa |
| Abstract | Leveraging the power of big data represents an opportunity for brand managers to reveal patterns and trends in consumer perceptions, while monitoring positive or negative associations of the brand with desired topics. This paper describes the functionalities of the SBS Brand Intelligence App (SBS BI), which has been designed to assess brand importance and provide brand analytics through the analysis of (big) textual data. To better describe the SBS BI’s functionalities, we present a case study focused on the 2020 US Democratic Presidential Primaries. We downloaded 50,000 online articles from the Event Registry database, which contains both mainstream and blog news collected from around the world. These online news articles were transformed into networks of co-occurring words and analyzed by combining methods and tools from social network analysis and text mining. |
| Tasks | |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11479v1 |
| https://arxiv.org/pdf/2001.11479v1.pdf | |
| PWC | https://paperswithcode.com/paper/brand-intelligence-analytics |
| Repo | |
| Framework | |
Interventions and Counterfactuals in Tractable Probabilistic Models: Limitations of Contemporary Transformations
| Title | Interventions and Counterfactuals in Tractable Probabilistic Models: Limitations of Contemporary Transformations |
| Authors | Ioannis Papantonis, Vaishak Belle |
| Abstract | In recent years, there has been an increasing interest in studying causality-related properties in machine learning models generally, and in generative models in particular. While that is well motivated, it inherits the fundamental computational hardness of probabilistic inference, making exact reasoning intractable. Probabilistic tractable models have also recently emerged, which guarantee that conditional marginals can be computed in time linear in the size of the model, where the model is usually learned from data. Although initially limited to low tree-width models, recent tractable models such as sum product networks (SPNs) and probabilistic sentential decision diagrams (PSDDs) exploit efficient function representations and also capture high tree-width models. In this paper, we ask the following technical question: can we use the distributions represented or learned by these models to perform causal queries, such as reasoning about interventions and counterfactuals? By appealing to some existing ideas on transforming such models to Bayesian networks, we answer mostly in the negative. We show that when transforming SPNs to a causal graph interventional reasoning reduces to computing marginal distributions; in other words, only trivial causal reasoning is possible. For PSDDs the situation is only slightly better. We first provide an algorithm for constructing a causal graph from a PSDD, which introduces augmented variables. Intervening on the original variables, once again, reduces to marginal distributions, but when intervening on the augmented variables, a deterministic but nonetheless causal-semantics can be provided for PSDDs. |
| Tasks | |
| Published | 2020-01-29 |
| URL | https://arxiv.org/abs/2001.10905v1 |
| https://arxiv.org/pdf/2001.10905v1.pdf | |
| PWC | https://paperswithcode.com/paper/interventions-and-counterfactuals-in |
| Repo | |
| Framework | |
