Paper Group ANR 691
Comparative Evaluation of Multiagent Learning Algorithms in a Diverse Set of Ad Hoc Team Problems. Co-Attentive Cross-Modal Deep Learning for Medical Evidence Synthesis and Decision Making. Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path at Long Standoff Distances. Deep-learning PDEs with unlabe …
Comparative Evaluation of Multiagent Learning Algorithms in a Diverse Set of Ad Hoc Team Problems
| Title | Comparative Evaluation of Multiagent Learning Algorithms in a Diverse Set of Ad Hoc Team Problems |
| Authors | Stefano V. Albrecht, Subramanian Ramamoorthy |
| Abstract | This paper is concerned with evaluating different multiagent learning (MAL) algorithms in problems where individual agents may be heterogenous, in the sense of utilizing different learning strategies, without the opportunity for prior agreements or information regarding coordination. Such a situation arises in ad hoc team problems, a model of many practical multiagent systems applications. Prior work in multiagent learning has often been focussed on homogeneous groups of agents, meaning that all agents were identical and a priori aware of this fact. Also, those algorithms that are specifically designed for ad hoc team problems are typically evaluated in teams of agents with fixed behaviours, as opposed to agents which are adapting their behaviours. In this work, we empirically evaluate five MAL algorithms, representing major approaches to multiagent learning but originally developed with the homogeneous setting in mind, to understand their behaviour in a set of ad hoc team problems. All teams consist of agents which are continuously adapting their behaviours. The algorithms are evaluated with respect to a comprehensive characterisation of repeated matrix games, using performance criteria that include considerations such as attainment of equilibrium, social welfare and fairness. Our main conclusion is that there is no clear winner. However, the comparative evaluation also highlights the relative strengths of different algorithms with respect to the type of performance criteria, e.g., social welfare vs. attainment of equilibrium. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09189v1 |
| https://arxiv.org/pdf/1907.09189v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-evaluation-of-multiagent-learning |
| Repo | |
| Framework | |
Co-Attentive Cross-Modal Deep Learning for Medical Evidence Synthesis and Decision Making
| Title | Co-Attentive Cross-Modal Deep Learning for Medical Evidence Synthesis and Decision Making |
| Authors | Devin Taylor, Simeon Spasov, Pietro Liò |
| Abstract | Modern medicine requires generalised approaches to the synthesis and integration of multimodal data, often at different biological scales, that can be applied to a variety of evidence structures, such as complex disease analyses and epidemiological models. However, current methods are either slow and expensive, or ineffective due to the inability to model the complex relationships between data modes which differ in scale and format. We address these issues by proposing a cross-modal deep learning architecture and co-attention mechanism to accurately model the relationships between the different data modes, while further reducing patient diagnosis time. Differentiating Parkinson’s Disease (PD) patients from healthy patients forms the basis of the evaluation. The model outperforms the previous state-of-the-art unimodal analysis by 2.35%, while also being 53% more parameter efficient than the industry standard cross-modal model. Furthermore, the evaluation of the attention coefficients allows for qualitative insights to be obtained. Through the coupling with bioinformatics, a novel link between the interferon-gamma-mediated pathway, DNA methylation and PD was identified. We believe that our approach is general and could optimise the process of medical evidence synthesis and decision making in an actionable way. |
| Tasks | Decision Making |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06442v2 |
| https://arxiv.org/pdf/1909.06442v2.pdf | |
| PWC | https://paperswithcode.com/paper/co-attentive-cross-modal-deep-learning-for |
| Repo | |
| Framework | |
Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path at Long Standoff Distances
| Title | Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path at Long Standoff Distances |
| Authors | Christopher A. Metzler, David B. Lindell, Gordon Wetzstein |
| Abstract | Non-line-of-sight (NLOS) imaging and tracking is an emerging paradigm that allows the shape or position of objects around corners or behind diffusers to be recovered from transient measurements. However, existing NLOS approaches require the imaging system to scan a large area on a visible surface, where the indirect light paths of hidden objects are sampled. In many applications, such as robotic vision or autonomous driving, optical access to a large scanning area may not be available, which severely limits the practicality of existing NLOS techniques. Here, we propose a new approach, dubbed keyhole imaging, that captures a sequence of transient measurements along a single optical path at long standoff distances, for example through a keyhole. Assuming that the hidden object of interest moves during the acquisition time, we capture a series of time-resolved projections of the object’s shape from unknown viewpoints. We derive inverse methods based on Expectation-Maximization to recover the object’s shape and location using these measurements, and we demonstrate successful experimental results with a prototype keyhole imaging system. |
| Tasks | Autonomous Driving |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06727v1 |
| https://arxiv.org/pdf/1912.06727v1.pdf | |
| PWC | https://paperswithcode.com/paper/keyhole-imaging-non-line-of-sight-imaging-and |
| Repo | |
| Framework | |
Deep-learning PDEs with unlabeled data and hardwiring physics laws
| Title | Deep-learning PDEs with unlabeled data and hardwiring physics laws |
| Authors | S. Mohammad H. Hashemi, Demetri Psaltis |
| Abstract | Providing fast and accurate solutions to partial differential equations is a problem of continuous interest to the fields of applied mathematics and physics. With the recent advances in machine learning, the adoption learning techniques in this domain is being eagerly pursued. We build upon earlier works on linear and homogeneous PDEs, and develop convolutional deep neural networks that can accurately solve nonlinear and non-homogeneous equations without the need for labeled data. The architecture of these networks is readily accessible for scientific disciplines who deal with PDEs and know the basics of deep learning. |
| Tasks | |
| Published | 2019-04-13 |
| URL | http://arxiv.org/abs/1904.06578v1 |
| http://arxiv.org/pdf/1904.06578v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-pdes-with-unlabeled-data-and |
| Repo | |
| Framework | |
VOnDA: A Framework for Ontology-Based Dialogue Management
| Title | VOnDA: A Framework for Ontology-Based Dialogue Management |
| Authors | Bernd Kiefer, Anna Welker, Christophe Biwer |
| Abstract | We present VOnDA, a framework to implement the dialogue management functionality in dialogue systems. Although domain-independent, VOnDA is tailored towards dialogue systems with a focus on social communication, which implies the need of long-term memory and high user adaptivity. For these systems, which are used in health environments or elderly care, margin of error is very low and control over the dialogue process is of topmost importance. The same holds for commercial applications, where customer trust is at risk. VOnDA’s specification and memory layer relies upon (extended) RDF/OWL, which provides a universal and uniform representation, and facilitates interoperability with external data sources, e.g., from physical sensors. |
| Tasks | Dialogue Management |
| Published | 2019-10-01 |
| URL | https://arxiv.org/abs/1910.00340v1 |
| https://arxiv.org/pdf/1910.00340v1.pdf | |
| PWC | https://paperswithcode.com/paper/vonda-a-framework-for-ontology-based-dialogue |
| Repo | |
| Framework | |
Identifying cross country skiing techniques using power meters in ski poles
| Title | Identifying cross country skiing techniques using power meters in ski poles |
| Authors | Moa Johansson, Marie Korneliusson, Nickey Lizbat Lawrence |
| Abstract | Power meters are becoming a widely used tool for measuring training and racing effort in cycling, and are now spreading also to other sports. This means that increasing volumes of data can be collected from athletes, with the aim of helping coaches and athletes analyse and understanding training load, racing efforts, technique etc. In this project, we have collaborated with Skisens AB, a company producing handles for cross country ski poles equipped with power meters. We have conducted a pilot study in the use of machine learning techniques on data from Skisens poles to identify which “gear” a skier is using (double poling or gears 2-4 in skating), based only on the sensor data from the ski poles. The dataset for this pilot study contained labelled time-series data from three individual skiers using four different gears recorded in varied locations and varied terrain. We systematically evaluated a number of machine learning techniques based on neural networks with best results obtained by a LSTM network (accuracy of 95% correctly classified strokes), when a subset of data from all three skiers was used for training. As expected, accuracy dropped to 78% when the model was trained on data from only two skiers and tested on the third. To achieve better generalisation to individuals not appearing in the training set more data is required, which is ongoing work. |
| Tasks | Time Series |
| Published | 2019-04-23 |
| URL | https://arxiv.org/abs/1904.10359v2 |
| https://arxiv.org/pdf/1904.10359v2.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-cross-country-skiing-techniques |
| Repo | |
| Framework | |
Imaging and Classification Techniques for Seagrass Mapping and Monitoring: A Comprehensive Survey
| Title | Imaging and Classification Techniques for Seagrass Mapping and Monitoring: A Comprehensive Survey |
| Authors | Md Moniruzzaman, S. M. Shamsul Islam, Paul Lavery, Mohammed Bennamoun, C. Peng Lam |
| Abstract | Monitoring underwater habitats is a vital part of observing the condition of the environment. The detection and mapping of underwater vegetation, especially seagrass has drawn the attention of the research community as early as the nineteen eighties. Initially, this monitoring relied on in situ observation by experts. Later, advances in remote-sensing technology, satellite-monitoring techniques and, digital photo- and video-based techniques opened a window to quicker, cheaper, and, potentially, more accurate seagrass-monitoring methods. So far, for seagrass detection and mapping, digital images from airborne cameras, spectral images from satellites, acoustic image data using underwater sonar technology, and digital underwater photo and video images have been used to map the seagrass meadows or monitor their condition. In this article, we have reviewed the recent approaches to seagrass detection and mapping to understand the gaps of the present approaches and determine further research scope to monitor the ocean health more easily. We have identified four classes of approach to seagrass mapping and assessment: still image-, video data-, acoustic image-, and spectral image data-based techniques. We have critically analysed the surveyed approaches and found the research gaps including the need for quick, cheap and effective imaging techniques robust to depth, turbidity, location and weather conditions, fully automated seagrass detectors that can work in real-time, accurate techniques for estimating the seagrass density, and the availability of high computation facilities for processing large scale data. For addressing these gaps, future research should focus on developing cheaper image and video data collection techniques, deep learning based automatic annotation and classification, and real-time percentage-cover calculation. |
| Tasks | |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.11114v2 |
| http://arxiv.org/pdf/1902.11114v2.pdf | |
| PWC | https://paperswithcode.com/paper/imaging-and-classification-techniques-for |
| Repo | |
| Framework | |
Robust Invisible Hyperlinks in Physical Photographs Based on 3D Rendering Attacks
| Title | Robust Invisible Hyperlinks in Physical Photographs Based on 3D Rendering Attacks |
| Authors | Jun Jia, Zhongpai Gao, Kang Chen, Menghan Hu, Guangtao Zhai, Guodong Guo, Xiaokang Yang |
| Abstract | In the era of multimedia and Internet, people are eager to obtain information from offline to online. Quick Response (QR) codes and digital watermarks help us access information quickly. However, QR codes look ugly and invisible watermarks can be easily broken in physical photographs. Therefore, this paper proposes a novel method to embed hyperlinks into natural images, making the hyperlinks invisible for human eyes but detectable for mobile devices. Our method is an end-to-end neural network with an encoder to hide information and a decoder to recover information. From original images to physical photographs, camera imaging process will introduce a series of distortion such as noise, blur, and light. To train a robust decoder against the physical distortion from the real world, a distortion network based on 3D rendering is inserted between the encoder and the decoder to simulate the camera imaging process. Besides, in order to maintain the visual attraction of the image with hyperlinks, we propose a loss function based on just noticeable difference (JND) to supervise the training of encoder. Experimental results show that our approach outperforms the previous method in both simulated and real situations. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01224v1 |
| https://arxiv.org/pdf/1912.01224v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-invisible-hyperlinks-in-physical |
| Repo | |
| Framework | |
RankQA: Neural Question Answering with Answer Re-Ranking
| Title | RankQA: Neural Question Answering with Answer Re-Ranking |
| Authors | Bernhard Kratzwald, Anna Eigenmann, Stefan Feuerriegel |
| Abstract | The conventional paradigm in neural question answering (QA) for narrative content is limited to a two-stage process: first, relevant text passages are retrieved and, subsequently, a neural network for machine comprehension extracts the likeliest answer. However, both stages are largely isolated in the status quo and, hence, information from the two phases is never properly fused. In contrast, this work proposes RankQA: RankQA extends the conventional two-stage process in neural QA with a third stage that performs an additional answer re-ranking. The re-ranking leverages different features that are directly extracted from the QA pipeline, i.e., a combination of retrieval and comprehension features. While our intentionally simple design allows for an efficient, data-sparse estimation, it nevertheless outperforms more complex QA systems by a significant margin: in fact, RankQA achieves state-of-the-art performance on 3 out of 4 benchmark datasets. Furthermore, its performance is especially superior in settings where the size of the corpus is dynamic. Here the answer re-ranking provides an effective remedy against the underlying noise-information trade-off due to a variable corpus size. As a consequence, RankQA represents a novel, powerful, and thus challenging baseline for future research in content-based QA. |
| Tasks | Question Answering, Reading Comprehension |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.03008v2 |
| https://arxiv.org/pdf/1906.03008v2.pdf | |
| PWC | https://paperswithcode.com/paper/rankqa-neural-question-answering-with-answer |
| Repo | |
| Framework | |
Learn a Prior for RHEA for Better Online Planning
| Title | Learn a Prior for RHEA for Better Online Planning |
| Authors | Xin Tong, Weiming Liu, Bin Li |
| Abstract | Rolling Horizon Evolutionary Algorithms (RHEA) are a class of online planning methods for real-time game playing; their performance is closely related to the planning horizon and the search time allowed. In this paper, we propose to learn a prior for RHEA in an offline manner by training a value network and a policy network. The value network is used to reduce the planning horizon by providing an estimation of future rewards, and the policy network is used to initialize the population, which helps to narrow down the search scope. The proposed algorithm, named prior-based RHEA (p-RHEA), trains policy and value networks by performing planning and learning iteratively. In the planning stage, the horizon-limited search assisted with the policy network and value network is performed to improve the policies and collect training samples. In the learning stage, the policy network and value network are trained with the collected samples to learn better prior knowledge. Experimental results on OpenAI Gym MuJoCo tasks show that the performance of the proposed p-RHEA is significantly improved compared to that of RHEA. |
| Tasks | |
| Published | 2019-02-14 |
| URL | http://arxiv.org/abs/1902.05284v2 |
| http://arxiv.org/pdf/1902.05284v2.pdf | |
| PWC | https://paperswithcode.com/paper/learn-a-prior-for-rhea-for-better-online |
| Repo | |
| Framework | |
A new neural-network-based model for measuring the strength of a pseudorandom binary sequence
| Title | A new neural-network-based model for measuring the strength of a pseudorandom binary sequence |
| Authors | Ahmed Alamer, Ben Soh |
| Abstract | Maximum order complexity is an important tool for measuring the nonlinearity of a pseudorandom sequence. There is a lack of tools for predicting the strength of a pseudorandom binary sequence in an effective and efficient manner. To this end, this paper proposes a neural-network-based model for measuring the strength of a pseudorandom binary sequence. Using the Shrinking Generator (SG) keystream as pseudorandom binary sequences, then calculating the Unique Window Size (UWS) as a representation of Maximum order complexity, we demonstrate that the proposed model provides more accurate and efficient predictions (measurements) than a classical method for predicting the maximum order complexity. |
| Tasks | |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04195v1 |
| https://arxiv.org/pdf/1910.04195v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-neural-network-based-model-for |
| Repo | |
| Framework | |
TwitterMancer: Predicting Interactions on Twitter Accurately
| Title | TwitterMancer: Predicting Interactions on Twitter Accurately |
| Authors | Konstantinos Sotiropoulos, John W. Byers, Polyvios Pratikakis, Charalampos E. Tsourakakis |
| Abstract | This paper investigates the interplay between different types of user interactions on Twitter, with respect to predicting missing or unseen interactions. For example, given a set of retweet interactions between Twitter users, how accurately can we predict reply interactions? Is it more difficult to predict retweet or quote interactions between a pair of accounts? Also, how important is time locality, and which features of interaction patterns are most important to enable accurate prediction of specific Twitter interactions? Our empirical study of Twitter interactions contributes initial answers to these questions. We have crawled an extensive dataset of Greek-speaking Twitter accounts and their follow, quote, retweet, reply interactions over a period of a month. We find we can accurately predict many interactions of Twitter users. Interestingly, the most predictive features vary with the user profiles, and are not the same across all users. For example, for a pair of users that interact with a large number of other Twitter users, we find that certain “higher-dimensional” triads, i.e., triads that involve multiple types of interactions, are very informative, whereas for less active Twitter users, certain in-degrees and out-degrees play a major role. Finally, we provide various other insights on Twitter user behavior. Our code and data are available at https://github.com/twittermancer/. Keywords: Graph mining, machine learning, social media, social networks |
| Tasks | |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11119v1 |
| http://arxiv.org/pdf/1904.11119v1.pdf | |
| PWC | https://paperswithcode.com/paper/twittermancer-predicting-interactions-on |
| Repo | |
| Framework | |
Adversarial normalization for multi domain image segmentation
| Title | Adversarial normalization for multi domain image segmentation |
| Authors | Pierre-Luc Delisle, Benoit Anctil-Robitaille, Christian Desrosiers, Herve Lombaert |
| Abstract | Image normalization is a critical step in medical imaging. This step is often done on a per-dataset basis, preventing current segmentation algorithms from the full potential of exploiting jointly normalized information across multiple datasets. To solve this problem, we propose an adversarial normalization approach for image segmentation which learns common normalizing functions across multiple datasets while retaining image realism. The adversarial training provides an optimal normalizer that improves both the segmentation accuracy and the discrimination of unrealistic normalizing functions. Our contribution therefore leverages common imaging information from multiple domains. The optimality of our common normalizer is evaluated by combining brain images from both infants and adults. Results on the challenging iSEG and MRBrainS datasets reveal the potential of our adversarial normalization approach for segmentation, with Dice improvements of up to 59.6% over the baseline. |
| Tasks | Semantic Segmentation |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00993v2 |
| https://arxiv.org/pdf/1912.00993v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-normalization-for-multi-domain |
| Repo | |
| Framework | |
Adversarial dictionary learning for a robust analysis and modelling of spontaneous neuronal activity
| Title | Adversarial dictionary learning for a robust analysis and modelling of spontaneous neuronal activity |
| Authors | Eirini Troullinou, Grigorios Tsagkatakis, Ganna Palagina, Maria Papadopouli, Stelios Manolis Smirnakis, Panagiotis Tsakalides |
| Abstract | The field of neuroscience is experiencing rapid growth in the complexity and quantity of the recorded neural activity allowing us unprecedented access to its dynamics in different brain areas. The objective of this work is to discover directly from the experimental data rich and comprehensible models for brain function that will be concurrently robust to noise. Considering this task from the perspective of dimensionality reduction, we develop an innovative, robust to noise dictionary learning framework based on adversarial training methods for the identification of patterns of synchronous firing activity as well as within a time lag. We employ real-world binary datasets describing the spontaneous neuronal activity of laboratory mice over time, and we aim to their efficient low-dimensional representation. The results on the classification accuracy for the discrimination between the clean and the adversarial-noisy activation patterns obtained by an SVM classifier highlight the efficacy of the proposed scheme compared to other methods, and the visualization of the dictionary’s distribution demonstrates the multifarious information that we obtain from it. |
| Tasks | Dictionary Learning, Dimensionality Reduction |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.01721v2 |
| https://arxiv.org/pdf/1911.01721v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-dictionary-learning-for-a-robust |
| Repo | |
| Framework | |
Latent Part-of-Speech Sequences for Neural Machine Translation
| Title | Latent Part-of-Speech Sequences for Neural Machine Translation |
| Authors | Xuewen Yang, Yingru Liu, Dongliang Xie, Xin Wang, Niranjan Balasubramanian |
| Abstract | Learning target side syntactic structure has been shown to improve Neural Machine Translation (NMT). However, incorporating syntax through latent variables introduces additional complexity in inference, as the models need to marginalize over the latent syntactic structures. To avoid this, models often resort to greedy search which only allows them to explore a limited portion of the latent space. In this work, we introduce a new latent variable model, LaSyn, that captures the co-dependence between syntax and semantics, while allowing for effective and efficient inference over the latent space. LaSyn decouples direct dependence between successive latent variables, which allows its decoder to exhaustively search through the latent syntactic choices, while keeping decoding speed proportional to the size of the latent variable vocabulary. We implement LaSyn by modifying a transformer-based NMT system and design a neural expectation maximization algorithm that we regularize with part-of-speech information as the latent sequences. Evaluations on four different MT tasks show that incorporating target side syntax with LaSyn improves both translation quality, and also provides an opportunity to improve diversity. |
| Tasks | Machine Translation |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1908.11782v1 |
| https://arxiv.org/pdf/1908.11782v1.pdf | |
| PWC | https://paperswithcode.com/paper/latent-part-of-speech-sequences-for-neural |
| Repo | |
| Framework | |
