Paper Group ANR 680
AREA: Adaptive Reference-set Based Evolutionary Algorithm for Multiobjective Optimisation. A Passage-Based Approach to Learning to Rank Documents. Analyzing Bias in Sensitive Personal Information Used to Train Financial Models. Faster polytope rounding, sampling, and volume computation via a sublinear “Ball Walk”. Trends in the optimal location and …
AREA: Adaptive Reference-set Based Evolutionary Algorithm for Multiobjective Optimisation
| Title | AREA: Adaptive Reference-set Based Evolutionary Algorithm for Multiobjective Optimisation |
| Authors | Shouyong Jiang, Hongru Li, Jinglei Guo, Mingjun Zhong, Shengxiang Yang, Marcus Kaiser, Natalio Krasnogor |
| Abstract | Population-based evolutionary algorithms have great potential to handle multiobjective optimisation problems. However, these algorithms depends largely on problem characteristics, and there is a need to improve their performance for a wider range of problems. References, which are often specified by the decision maker’s preference in different forms, are a very effective method to improve the performance of algorithms but have not been fully explored in literature. This paper proposes a novel framework for effective use of references to strengthen algorithms. This framework considers references as search targets which can be adjusted based on the information collected during the search. The proposed framework is combined with new strategies, such as reference adaptation and adaptive local mating, to solve different types of problems. The proposed algorithm is compared with state of the arts on a wide range of problems with diverse characteristics. The comparison and extensive sensitivity analysis demonstrate that the proposed algorithm is competitive and robust across different types of problems studied in this paper. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.07491v1 |
| https://arxiv.org/pdf/1910.07491v1.pdf | |
| PWC | https://paperswithcode.com/paper/area-adaptive-reference-set-based |
| Repo | |
| Framework | |
A Passage-Based Approach to Learning to Rank Documents
| Title | A Passage-Based Approach to Learning to Rank Documents |
| Authors | Eilon Sheetrit, Anna Shtok, Oren Kurland |
| Abstract | According to common relevance-judgments regimes, such as TREC’s, a document can be deemed relevant to a query even if it contains a very short passage of text with pertinent information. This fact has motivated work on passage-based document retrieval: document ranking methods that induce information from the document’s passages. However, the main source of passage-based information utilized was passage-query similarities. We address the challenge of utilizing richer sources of passage-based information to improve document retrieval effectiveness. Specifically, we devise a suite of learning-to-rank-based document retrieval methods that utilize an effective ranking of passages produced in response to the query; the passage ranking is also induced using a learning-to-rank approach. Some of the methods quantify the ranking of the passages of a document. Others utilize the feature-based representation of passages used for learning a passage ranker. Empirical evaluation attests to the clear merits of our methods with respect to highly effective baselines. Our best performing method is based on learning a document ranking function using document-query features and passage-query features of the document’s passage most highly ranked. |
| Tasks | Document Ranking, Learning-To-Rank |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02083v1 |
| https://arxiv.org/pdf/1906.02083v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-passage-based-approach-to-learning-to-rank |
| Repo | |
| Framework | |
Analyzing Bias in Sensitive Personal Information Used to Train Financial Models
| Title | Analyzing Bias in Sensitive Personal Information Used to Train Financial Models |
| Authors | Reginald Bryant, Celia Cintas, Isaac Wambugu, Andrew Kinai, Komminist Weldemariam |
| Abstract | Bias in data can have unintended consequences that propagate to the design, development, and deployment of machine learning models. In the financial services sector, this can result in discrimination from certain financial instruments and services. At the same time, data privacy is of paramount importance, and recent data breaches have seen reputational damage for large institutions. Presented in this paper is a trusted model-lifecycle management platform that attempts to ensure consumer data protection, anonymization, and fairness. Specifically, we examine how datasets can be reproduced using deep learning techniques to effectively retain important statistical features in datasets whilst simultaneously protecting data privacy and enabling safe and secure sharing of sensitive personal information beyond the current state-of-practice. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03623v1 |
| https://arxiv.org/pdf/1911.03623v1.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-bias-in-sensitive-personal |
| Repo | |
| Framework | |
Faster polytope rounding, sampling, and volume computation via a sublinear “Ball Walk”
| Title | Faster polytope rounding, sampling, and volume computation via a sublinear “Ball Walk” |
| Authors | Oren Mangoubi, Nisheeth K. Vishnoi |
| Abstract | We study the problem of “isotropically rounding” a polytope $K\subset\mathbb{R}^n$, that is, computing a linear transformation which makes the uniform distribution on the polytope have roughly identity covariance matrix. We assume $K$ is defined by $m$ linear inequalities, with guarantee that $rB\subset K\subset RB$, where $B$ is the unit ball. We introduce a new variant of the ball walk Markov chain and show that, roughly, the expected number of arithmetic operations per-step of this Markov chain is $O(m)$ that is sublinear in the input size $mn$–the per-step time of all prior Markov chains. Subsequently, we give a rounding algorithm that succeeds with probability $1-\varepsilon$ in $\tilde{O}(mn^{4.5}\mbox{polylog}(\frac{1}{\varepsilon},\frac{R}{r}))$ arithmetic operations. This gives a factor of $\sqrt{n}$ improvement on the previous bound of $\tilde{O}(mn^5\mbox{polylog}(\frac{1}{\varepsilon},\frac{R}{r}))$ for rounding, which uses the hit-and-run algorithm. Since the rounding preprocessing step is in many cases the bottleneck in improving sampling or volume computation, our results imply these tasks can also be achieved in roughly $\tilde{O}(mn^{4.5}\mbox{polylog}(\frac{1}{\varepsilon},\frac{R}{r})+mn^4\delta^{-2})$ operations for computing the volume of $K$ up to a factor $1+\delta$ and $\tilde{O}(mn^{4.5}\mbox{polylog}(\frac{1}{\varepsilon},\frac{R}{r})))$ for uniformly sampling on $K$ with TV error $\varepsilon$. This improves on the previous bounds of $\tilde{O}(mn^5\mbox{polylog}(\frac{1}{\varepsilon},\frac{R}{r})+mn^4\delta^{-2})$ for volume computation when roughly $m\geq n^{2.5}$, and $\tilde{O}(mn^5\mbox{polylog}(\frac{1}{\varepsilon},\frac{R}{r}))$ for sampling when roughly $m\geq n^{1.5}$. We achieve this improvement by a novel method of computing polytope membership, where one avoids checking inequalities estimated to have a very low probability of being violated. |
| Tasks | |
| Published | 2019-05-05 |
| URL | https://arxiv.org/abs/1905.01745v2 |
| https://arxiv.org/pdf/1905.01745v2.pdf | |
| PWC | https://paperswithcode.com/paper/faster-algorithms-for-polytope-rounding |
| Repo | |
| Framework | |
Trends in the optimal location and sizing of electrical units in smart grids using meta-heuristic algorithms
| Title | Trends in the optimal location and sizing of electrical units in smart grids using meta-heuristic algorithms |
| Authors | Kayode Adetunji, Ivan Hofsajer, Ling Cheng |
| Abstract | The development of smart grids has effectively transformed the traditional grid system. This promises numerous advantages for economic values and autonomous control of energy sources. In smart grids development, there are various objectives such as voltage stability, minimized power loss, minimized economic cost and voltage profile improvement. Thus, researchers have investigated several approaches based on meta-heuristic optimization algorithms for the optimal location and sizing of electrical units in a distribution system. Meta-heuristic algorithms have been applied to solve different problems in power systems and they have been successfully used in distribution systems. This paper presents a comprehensive review on existing methods for the optimal location and sizing of electrical units in distribution networks while considering the improvement of major objective functions. Techniques such as voltage stability index, power loss index, and loss sensitivity factors have been implemented alongside the meta-heuristic optimization algorithms to reduce the search space of solutions for objective functions. However, these techniques can cause a loss of optimality. Another perceived problem is the inappropriate handling of multiple objectives, which can also affect the optimality of results. Hence, a recent method such as Pareto fronts generation has been developed to produce non-dominating solutions. This review shows a need for more research on (i) the effective handling of multiple objective functions, (ii) more efficient meta-heuristic optimization algorithms and/or (iii) better supporting techniques. |
| Tasks | |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.09312v1 |
| https://arxiv.org/pdf/1910.09312v1.pdf | |
| PWC | https://paperswithcode.com/paper/trends-in-the-optimal-location-and-sizing-of |
| Repo | |
| Framework | |
Real-time Multi-target Path Prediction and Planning for Autonomous Driving aided by FCN
| Title | Real-time Multi-target Path Prediction and Planning for Autonomous Driving aided by FCN |
| Authors | Hongtu Zhou, Xinneng Yang, Enwei Zhang, Junqiao Zhao, Lewen Cai, Chen Ye, Yan Wu |
| Abstract | Real-time multi-target path planning is a key issue in the field of autonomous driving. Although multiple paths can be generated in real-time with polynomial curves, the generated paths are not flexible enough to deal with complex road scenes such as S-shaped road and unstructured scenes such as parking lots. Search and sampling-based methods, such as A* and RRT and their derived methods, are flexible in generating paths for these complex road environments. However, the existing algorithms require significant time to plan to multiple targets, which greatly limits their application in autonomous driving. In this paper, a real-time path planning method for multi-targets is proposed. We train a fully convolutional neural network (FCN) to predict a path region for the target at first. By taking the predicted path region as soft constraints, the A* algorithm is then applied to search the exact path to the target. Experiments show that FCN can make multiple predictions in a very short time (50 times in 40ms), and the predicted path region effectively restrict the searching space for the following A* search. Therefore, the A* can search much faster so that the multi-target path planning can be achieved in real-time (3 targets in less than 100ms). |
| Tasks | Autonomous Driving |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07592v1 |
| https://arxiv.org/pdf/1909.07592v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-multi-target-path-prediction-and |
| Repo | |
| Framework | |
Learning to Rank for Plausible Plausibility
| Title | Learning to Rank for Plausible Plausibility |
| Authors | Zhongyang Li, Tongfei Chen, Benjamin Van Durme |
| Abstract | Researchers illustrate improvements in contextual encoding strategies via resultant performance on a battery of shared Natural Language Understanding (NLU) tasks. Many of these tasks are of a categorical prediction variety: given a conditioning context (e.g., an NLI premise), provide a label based on an associated prompt (e.g., an NLI hypothesis). The categorical nature of these tasks has led to common use of a cross entropy log-loss objective during training. We suggest this loss is intuitively wrong when applied to plausibility tasks, where the prompt by design is neither categorically entailed nor contradictory given the context. Log-loss naturally drives models to assign scores near 0.0 or 1.0, in contrast to our proposed use of a margin-based loss. Following a discussion of our intuition, we describe a confirmation study based on an extreme, synthetically curated task derived from MultiNLI. We find that a margin-based loss leads to a more plausible model of plausibility. Finally, we illustrate improvements on the Choice Of Plausible Alternative (COPA) task through this change in loss. |
| Tasks | Learning-To-Rank |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02079v1 |
| https://arxiv.org/pdf/1906.02079v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-rank-for-plausible-plausibility |
| Repo | |
| Framework | |
A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving
| Title | A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving |
| Authors | Florin Leon, Marius Gavrilescu |
| Abstract | This literature review focuses on three important aspects of an autonomous car system: tracking (assessing the identity of the actors such as cars, pedestrians or obstacles in a sequence of observations), prediction (predicting the future motion of surrounding vehicles in order to navigate through various traffic scenarios) and decision making (analyzing the available actions of the ego car and their consequences to the entire driving context). For tracking and prediction, approaches based on (deep) neural networks and other, especially stochastic techniques, are reported. For decision making, deep reinforcement learning algorithms are presented, together with methods used to explore different alternative actions, such as Monte Carlo Tree Search. |
| Tasks | Autonomous Driving, Decision Making |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07707v1 |
| https://arxiv.org/pdf/1909.07707v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-review-of-tracking-prediction-and-decision |
| Repo | |
| Framework | |
Towards Automatic Detection of Misinformation in Online Medical Videos
| Title | Towards Automatic Detection of Misinformation in Online Medical Videos |
| Authors | Rui Hou, Verónica Pérez-Rosas, Stacy Loeb, Rada Mihalcea |
| Abstract | Recent years have witnessed a significant increase in the online sharing of medical information, with videos representing a large fraction of such online sources. Previous studies have however shown that more than half of the health-related videos on platforms such as YouTube contain misleading information and biases. Hence, it is crucial to build computational tools that can help evaluate the quality of these videos so that users can obtain accurate information to help inform their decisions. In this study, we focus on the automatic detection of misinformation in YouTube videos. We select prostate cancer videos as our entry point to tackle this problem. The contribution of this paper is twofold. First, we introduce a new dataset consisting of 250 videos related to prostate cancer manually annotated for misinformation. Second, we explore the use of linguistic, acoustic, and user engagement features for the development of classification models to identify misinformation. Using a series of ablation experiments, we show that we can build automatic models with accuracies of up to 74%, corresponding to a 76.5% precision and 73.2% recall for misinformative instances. |
| Tasks | |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01543v1 |
| https://arxiv.org/pdf/1909.01543v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-automatic-detection-of-misinformation |
| Repo | |
| Framework | |
Generating Optimal Privacy-Protection Mechanisms via Machine Learning
| Title | Generating Optimal Privacy-Protection Mechanisms via Machine Learning |
| Authors | Marco Romanelli, Catuscia Palamidessi, Konstantinos Chatzikokolakis |
| Abstract | We consider the problem of obfuscating sensitive information while preserving utility. Given that an analytical solution is often not feasible because of un-scalability and because the background knowledge may be too complicated to determine, we propose an approach based on machine learning, inspired by the GANs (Generative Adversarial Networks) paradigm. The idea is to set up two nets: the generator, that tries to produce an optimal obfuscation mechanism to protect the data, and the classifier, that tries to de-obfuscate the data. By letting the two nets compete against each other, the mechanism improves its degree of protection, until an equilibrium is reached. We apply our method to the case of location privacy, and we perform experiments on synthetic data and on real data from the Gowalla dataset. We evaluate the privacy of the mechanism not only by its capacity to defeat the classificator, but also in terms of the Bayes error, which represents the strongest possible adversary. We compare the privacy-utility tradeoff of our method with that of the planar Laplace mechanism used in geo-indistinguishability, showing favorable results. |
| Tasks | |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.01059v1 |
| http://arxiv.org/pdf/1904.01059v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-optimal-privacy-protection |
| Repo | |
| Framework | |
An Adaptive Supervision Framework for Active Learning in Object Detection
| Title | An Adaptive Supervision Framework for Active Learning in Object Detection |
| Authors | Sai Vikas Desai, Akshay L Chandra, Wei Guo, Seishi Ninomiya, Vineeth N Balasubramanian |
| Abstract | Active learning approaches in computer vision generally involve querying strong labels for data. However, previous works have shown that weak supervision can be effective in training models for vision tasks while greatly reducing annotation costs. Using this knowledge, we propose an adaptive supervision framework for active learning and demonstrate its effectiveness on the task of object detection. Instead of directly querying bounding box annotations (strong labels) for the most informative samples, we first query weak labels and optimize the model. Using a switching condition, the required supervision level can be increased. Our framework requires little to no change in model architecture. Our extensive experiments show that the proposed framework can be used to train good generalizable models with much lesser annotation costs than the state of the art active learning approaches for object detection. |
| Tasks | Active Learning, Object Detection |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02454v3 |
| https://arxiv.org/pdf/1908.02454v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-adaptive-supervision-framework-for-active |
| Repo | |
| Framework | |
Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision
| Title | Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision |
| Authors | Fatemeh Pishdadian, Gordon Wichern, Jonathan Le Roux |
| Abstract | While there has been much recent progress using deep learning techniques to separate speech and music audio signals, these systems typically require large collections of isolated sources during the training process. When extending audio source separation algorithms to more general domains such as environmental monitoring, it may not be possible to obtain isolated signals for training. Here, we propose objective functions and network architectures that enable training a source separation system with weak labels. In this scenario, weak labels are defined in contrast with strong time-frequency (TF) labels such as those obtained from isolated sources, and refer either to frame-level weak labels where one only has access to the time periods when different sources are active in an audio mixture, or to clip-level weak labels that only indicate the presence or absence of sounds in an entire audio clip. We train a separator that estimates a TF mask for each type of sound event, using a sound event classifier as an assessor of the separator’s performance to bridge the gap between the TF-level separation and the ground truth weak labels only available at the frame or clip level. Our objective function requires the classifier applied to a separated source to assign high probability to the class corresponding to that source and low probability to all other classes. The objective function also enforces that the separated sources sum up to the mixture. We benchmark the performance of our algorithm using synthetic mixtures of overlapping events created from a database of sounds recorded in urban environments. Compared to training a network using isolated sources, our model achieves somewhat lower but still significant SI-SDR improvement, even in scenarios with significant sound event overlap. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02182v1 |
| https://arxiv.org/pdf/1911.02182v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-strength-in-weakness-learning-to |
| Repo | |
| Framework | |
The 1/5-th Rule with Rollbacks: On Self-Adjustment of the Population Size in the $(1+(λ,λ))$ GA
| Title | The 1/5-th Rule with Rollbacks: On Self-Adjustment of the Population Size in the $(1+(λ,λ))$ GA |
| Authors | Anton Bassin, Maxim Buzdalov |
| Abstract | Self-adjustment of parameters can significantly improve the performance of evolutionary algorithms. A notable example is the $(1+(\lambda,\lambda))$ genetic algorithm, where the adaptation of the population size helps to achieve the linear runtime on the OneMax problem. However, on problems which interfere with the assumptions behind the self-adjustment procedure, its usage can lead to performance degradation compared to static parameter choices. In particular, the one fifth rule, which guides the adaptation in the example above, is able to raise the population size too fast on problems which are too far away from the perfect fitness-distance correlation. We propose a modification of the one fifth rule in order to have less negative impact on the performance in scenarios when the original rule reduces the performance. Our modification, while still having a good performance on OneMax, both theoretically and in practice, also shows better results on linear functions with random weights and on random satisfiable MAX-SAT instances. |
| Tasks | |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.07284v1 |
| http://arxiv.org/pdf/1904.07284v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-15-th-rule-with-rollbacks-on-self |
| Repo | |
| Framework | |
Estimation of the yield curve for Costa Rica using combinatorial optimization metaheuristics applied to nonlinear regression
| Title | Estimation of the yield curve for Costa Rica using combinatorial optimization metaheuristics applied to nonlinear regression |
| Authors | Andres Quiros-Granados, JAvier Trejos-Zelaya |
| Abstract | The term structure of interest rates or yield curve is a function relating the interest rate with its own term. Nonlinear regression models of Nelson-Siegel and Svensson were used to estimate the yield curve using a sample of historical data supplied by the National Stock Exchange of Costa Rica. The optimization problem involved in the estimation process of model parameters is addressed by the use of four well known combinatorial optimization metaheuristics: Ant colony optimization, Genetic algorithm, Particle swarm optimization and Simulated annealing. The aim of the study is to improve the local minima obtained by a classical quasi-Newton optimization method using a descent direction. Good results with at least two metaheuristics are achieved, Particle swarm optimization and Simulated annealing. Keywords: Yield curve, nonlinear regression, Nelson- |
| Tasks | Combinatorial Optimization |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/2001.00920v1 |
| https://arxiv.org/pdf/2001.00920v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-of-the-yield-curve-for-costa-rica |
| Repo | |
| Framework | |
CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions
| Title | CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions |
| Authors | Tom Vercauteren, Mathias Unberath, Nicolas Padoy, Nassir Navab |
| Abstract | Data-driven computational approaches have evolved to enable extraction of information from medical images with a reliability, accuracy and speed which is already transforming their interpretation and exploitation in clinical practice. While similar benefits are longed for in the field of interventional imaging, this ambition is challenged by a much higher heterogeneity. Clinical workflows within interventional suites and operating theatres are extremely complex and typically rely on poorly integrated intra-operative devices, sensors, and support infrastructures. Taking stock of some of the most exciting developments in machine learning and artificial intelligence for computer assisted interventions, we highlight the crucial need to take context and human factors into account in order to address these challenges. Contextual artificial intelligence for computer assisted intervention, or CAI4CAI, arises as an emerging opportunity feeding into the broader field of surgical data science. Central challenges being addressed in CAI4CAI include how to integrate the ensemble of prior knowledge and instantaneous sensory information from experts, sensors and actuators; how to create and communicate a faithful and actionable shared representation of the surgery among a mixed human-AI actor team; how to design interventional systems and associated cognitive shared control schemes for online uncertainty-aware collaborative decision making ultimately producing more precise and reliable interventions. |
| Tasks | Decision Making |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.09031v1 |
| https://arxiv.org/pdf/1910.09031v1.pdf | |
| PWC | https://paperswithcode.com/paper/cai4cai-the-rise-of-contextual-artificial |
| Repo | |
| Framework | |
