Paper Group ANR 144
TTDM: A Travel Time Difference Model for Next Location Prediction. Rat big, cat eaten! Ideas for a useful deep-agent protolanguage. Probabilistic forecasting approaches for extreme NO$_2$ episodes: a comparison of models. Interference Classification Using Deep Neural Networks. A Distributionally Robust Area Under Curve Maximization Model. Support-w …
TTDM: A Travel Time Difference Model for Next Location Prediction
| Title | TTDM: A Travel Time Difference Model for Next Location Prediction |
| Authors | Qingjie Liu, Yixuan Zuo, Xiaohui Yu, Meng Chen |
| Abstract | Next location prediction is of great importance for many location-based applications and provides essential intelligence to business and governments. In existing studies, a common approach to next location prediction is to learn the sequential transitions with massive historical trajectories based on conditional probability. Unfortunately, due to the time and space complexity, these methods (e.g., Markov models) only use the just passed locations to predict next locations, without considering all the passed locations in the trajectory. In this paper, we seek to enhance the prediction performance by considering the travel time from all the passed locations in the query trajectory to a candidate next location. In particular, we propose a novel method, called Travel Time Difference Model (TTDM), which exploits the difference between the shortest travel time and the actual travel time to predict next locations. Further, we integrate the TTDM with a Markov model via a linear interpolation to yield a joint model, which computes the probability of reaching each possible next location and returns the top-rankings as results. We have conducted extensive experiments on two real datasets: the vehicle passage record (VPR) data and the taxi trajectory data. The experimental results demonstrate significant improvements in prediction accuracy over existing solutions. For example, compared with the Markov model, the top-1 accuracy improves by 40% on the VPR data and by 15.6% on the Taxi data. |
| Tasks | |
| Published | 2020-03-16 |
| URL | https://arxiv.org/abs/2003.07781v1 |
| https://arxiv.org/pdf/2003.07781v1.pdf | |
| PWC | https://paperswithcode.com/paper/ttdm-a-travel-time-difference-model-for-next |
| Repo | |
| Framework | |
Rat big, cat eaten! Ideas for a useful deep-agent protolanguage
| Title | Rat big, cat eaten! Ideas for a useful deep-agent protolanguage |
| Authors | Marco Baroni |
| Abstract | Deep-agent communities developing their own language-like communication protocol are a hot (or at least warm) topic in AI. Such agents could be very useful in machine-machine and human-machine interaction scenarios long before they have evolved a protocol as complex as human language. Here, I propose a small set of priorities we should focus on, if we want to get as fast as possible to a stage where deep agents speak a useful protolanguage. |
| Tasks | |
| Published | 2020-03-17 |
| URL | https://arxiv.org/abs/2003.11922v1 |
| https://arxiv.org/pdf/2003.11922v1.pdf | |
| PWC | https://paperswithcode.com/paper/rat-big-cat-eaten-ideas-for-a-useful-deep |
| Repo | |
| Framework | |
Probabilistic forecasting approaches for extreme NO$_2$ episodes: a comparison of models
| Title | Probabilistic forecasting approaches for extreme NO$_2$ episodes: a comparison of models |
| Authors | Sebastián Pérez Vasseur, José L. Aznarte |
| Abstract | High concentration episodes for NO$_2$ are increasingly dealt with by authorities through traffic restrictions which are activated when air quality deteriorates beyond certain thresholds. Foreseeing the probability that pollutant concentrations reach those thresholds becomes thus a necessity. Probabilistic forecasting is a family of techniques that allow for the prediction of the expected distribution function instead of a single value. In the case of NO$_2$, it allows for the calculation of future chances of exceeding thresholds and to detect pollution peaks. We thoroughly compared 10 state of the art probabilistic predictive models, using them to predict the distribution of NO$_2$ concentrations in a urban location for a set of forecasting horizons (up to 60 hours). Quantile gradient boosted trees shows the best performance, yielding the best results for both the expected value and the forecast full distribution. Furthermore, we show how this approach can be used to detect pollution peaks. |
| Tasks | |
| Published | 2020-03-24 |
| URL | https://arxiv.org/abs/2003.11356v1 |
| https://arxiv.org/pdf/2003.11356v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-forecasting-approaches-for |
| Repo | |
| Framework | |
Interference Classification Using Deep Neural Networks
| Title | Interference Classification Using Deep Neural Networks |
| Authors | Jianyuan Yu, Mohammad Alhassoun, R. Michael Buehrer |
| Abstract | The recent success in implementing supervised learning to classify modulation types suggests that other problems akin to modulation classification would eventually benefit from that implementation. One of these problems is classifying the interference type added to a signal-of-interest, also known as interference classification. In this paper, we propose an interference classification method using a deep neural network. We generate five distinct types of interfering signals then use both the power-spectral density (PSD) and the cyclic spectrum of the received signal as input features to the network. The computer experiments reveal that using the received signal PSD outperforms using its cyclic spectrum in terms of accuracy. In addition, the same experiments show that the feed-forward networks yield better accuracy than classic methods. The proposed classifier aids the subsequent stage in the receiver chain with choosing the appropriate mitigation algorithm and also can coexist with modulation-classification methods to further improve the classifier accuracy. |
| Tasks | |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00533v1 |
| https://arxiv.org/pdf/2002.00533v1.pdf | |
| PWC | https://paperswithcode.com/paper/interference-classification-using-deep-neural |
| Repo | |
| Framework | |
A Distributionally Robust Area Under Curve Maximization Model
| Title | A Distributionally Robust Area Under Curve Maximization Model |
| Authors | Wenbo Ma, Miguel A. Lejeune |
| Abstract | Area under ROC curve (AUC) is a widely used performance measure for classification models. We propose a new distributionally robust AUC maximization model (DR-AUC) that relies on the Kantorovich metric and approximates the AUC with the hinge loss function. We use duality theory to reformulate the DR-AUC model as a tractable convex quadratic optimization problem. The numerical experiments show that the proposed DR-AUC model – benchmarked with the standard deterministic AUC and the support vector machine models - improves the out-of-sample performance over the majority of the considered datasets. The results are particularly encouraging since our numerical experiments are conducted with training sets of small size which have been known to be conducive to low out-of-sample performance. |
| Tasks | |
| Published | 2020-02-18 |
| URL | https://arxiv.org/abs/2002.07345v1 |
| https://arxiv.org/pdf/2002.07345v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-distributionally-robust-area-under-curve |
| Repo | |
| Framework | |
Support-weighted Adversarial Imitation Learning
| Title | Support-weighted Adversarial Imitation Learning |
| Authors | Ruohan Wang, Carlo Ciliberto, Pierluigi Amadori, Yiannis Demiris |
| Abstract | Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of demonstrations, it faces several practical challenges such as potential training instability and implicit reward bias. To address the challenges, we propose Support-weighted Adversarial Imitation Learning (SAIL), a general framework that extends a given AIL algorithm with information derived from support estimation of the expert policies. SAIL improves the quality of the reinforcement signals by weighing the adversarial reward with a confidence score from support estimation of the expert policy. We also show that SAIL is always at least as efficient as the underlying AIL algorithm that SAIL uses for learning the adversarial reward. Empirically, we show that the proposed method achieves better performance and training stability than baseline methods on a wide range of benchmark control tasks. |
| Tasks | Imitation Learning |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.08803v1 |
| https://arxiv.org/pdf/2002.08803v1.pdf | |
| PWC | https://paperswithcode.com/paper/support-weighted-adversarial-imitation |
| Repo | |
| Framework | |
Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity
| Title | Approximate is Good Enough: Probabilistic Variants of Dimensional and Margin Complexity |
| Authors | Pritish Kamath, Omar Montasser, Nathan Srebro |
| Abstract | We present and study approximate notions of dimensional and margin complexity, which correspond to the minimal dimension or norm of an embedding required to approximate, rather then exactly represent, a given hypothesis class. We show that such notions are not only sufficient for learning using linear predictors or a kernel, but unlike the exact variants, are also necessary. Thus they are better suited for discussing limitations of linear or kernel methods. |
| Tasks | |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.04180v1 |
| https://arxiv.org/pdf/2003.04180v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-is-good-enough-probabilistic |
| Repo | |
| Framework | |
Covering the News with (AI) Style
| Title | Covering the News with (AI) Style |
| Authors | Michele Merler, Cicero Nogueira dos Santos, Mauro Martino, Alfio M. Gliozzo, John R. Smith |
| Abstract | We introduce a multi-modal discriminative and generative frame-work capable of assisting humans in producing visual content re-lated to a given theme, starting from a collection of documents(textual, visual, or both). This framework can be used by edit or to generate images for articles, as well as books or music album covers. Motivated by a request from the The New York Times (NYT) seeking help to use AI to create art for their special section on Artificial Intelligence, we demonstrated the application of our system in producing such image. |
| Tasks | |
| Published | 2020-01-05 |
| URL | https://arxiv.org/abs/2002.02369v1 |
| https://arxiv.org/pdf/2002.02369v1.pdf | |
| PWC | https://paperswithcode.com/paper/covering-the-news-with-ai-style |
| Repo | |
| Framework | |
Break It Down: A Question Understanding Benchmark
| Title | Break It Down: A Question Understanding Benchmark |
| Authors | Tomer Wolfson, Mor Geva, Ankit Gupta, Matt Gardner, Yoav Goldberg, Daniel Deutch, Jonathan Berant |
| Abstract | Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer. In this work, we introduce a Question Decomposition Meaning Representation (QDMR) for questions. QDMR constitutes the ordered list of steps, expressed through natural language, that are necessary for answering a question. We develop a crowdsourcing pipeline, showing that quality QDMRs can be annotated at scale, and release the Break dataset, containing over 83K pairs of questions and their QDMRs. We demonstrate the utility of QDMR by showing that (a) it can be used to improve open-domain question answering on the HotpotQA dataset, (b) it can be deterministically converted to a pseudo-SQL formal language, which can alleviate annotation in semantic parsing applications. Last, we use Break to train a sequence-to-sequence model with copying that parses questions into QDMR structures, and show that it substantially outperforms several natural baselines. |
| Tasks | Open-Domain Question Answering, Question Answering, Semantic Parsing |
| Published | 2020-01-31 |
| URL | https://arxiv.org/abs/2001.11770v1 |
| https://arxiv.org/pdf/2001.11770v1.pdf | |
| PWC | https://paperswithcode.com/paper/break-it-down-a-question-understanding |
| Repo | |
| Framework | |
An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers’ Outputs
| Title | An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers’ Outputs |
| Authors | You Huang, Yuanlong Yu |
| Abstract | Batch Normalization (BN) techniques have been proposed to reduce the so-called Internal Covariate Shift (ICS) by attempting to keep the distributions of layer outputs unchanged. Experiments have shown their effectiveness on training deep neural networks. However, since only the first two moments are controlled in these BN techniques, it seems that a weak constraint is imposed on layer distributions and furthermore whether such constraint can reduce ICS is unknown. Thus this paper proposes a measure for ICS by using the Earth Mover (EM) distance and then derives the upper and lower bounds for the measure to provide a theoretical analysis of BN. The upper bound has shown that BN techniques can control ICS only for the outputs with low dimensions and small noise whereas their control is NOT effective in other cases. This paper also proves that such control is just a bounding of ICS rather than a reduction of ICS. Meanwhile, the analysis shows that the high-order moments and noise, which BN cannot control, have great impact on the lower bound. Based on such analysis, this paper furthermore proposes an algorithm that unitizes the outputs with an adjustable parameter to further bound ICS in order to cope with the problems of BN. The upper bound for the proposed unitization is noise-free and only dominated by the parameter. Thus, the parameter can be trained to tune the bound and further to control ICS. Besides, the unitization is embedded into the framework of BN to reduce the information loss. The experiments show that this proposed algorithm outperforms existing BN techniques on CIFAR-10, CIFAR-100 and ImageNet datasets. |
| Tasks | |
| Published | 2020-01-09 |
| URL | https://arxiv.org/abs/2001.02814v1 |
| https://arxiv.org/pdf/2001.02814v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-internal-covariate-shift-bounding |
| Repo | |
| Framework | |
Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph
| Title | Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph |
| Authors | Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang |
| Abstract | A commonly observed problem with abstractive summarization is the distortion or fabrication of factual information in the article. This inconsistency between summary and original text has led to various concerns over its applicability. In this paper, we propose to boost factual correctness of summaries via the fusion of knowledge, i.e. extracted factual relations from the article. We present a Fact-Aware Summarization model, FASum. In this model, the knowledge information can be organically integrated into the summary generation process via neural graph computation and effectively improves the factual correctness. Empirical results show that FASum generates summaries with significantly higher factual correctness compared with state-of-the-art abstractive summarization systems, both under an independently trained factual correctness evaluator and human evaluation. For example, in CNN/DailyMail dataset, FASum obtains 1.2% higher fact correctness scores than UniLM and 4.5% higher than BottomUp. |
| Tasks | Abstractive Text Summarization |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08612v2 |
| https://arxiv.org/pdf/2003.08612v2.pdf | |
| PWC | https://paperswithcode.com/paper/boosting-factual-correctness-of-abstractive |
| Repo | |
| Framework | |
Audio-Visual-Olfactory Resource Allocation for Tri-modal Virtual Environments
| Title | Audio-Visual-Olfactory Resource Allocation for Tri-modal Virtual Environments |
| Authors | Efstratios Doukakis, Kurt Debattista, Thomas Bashford-Rogers, Amar Dhokia, Ali Asadipour, Alan Chalmers, Carlo Harvey |
| Abstract | Virtual Environments (VEs) provide the opportunity to simulate a wide range of applications, from training to entertainment, in a safe and controlled manner. For applications which require realistic representations of real world environments, the VEs need to provide multiple, physically accurate sensory stimuli. However, simulating all the senses that comprise the human sensory system (HSS) is a task that requires significant computational resources. Since it is intractable to deliver all senses at the highest quality, we propose a resource distribution scheme in order to achieve an optimal perceptual experience within the given computational budgets. This paper investigates resource balancing for multi-modal scenarios composed of aural, visual and olfactory stimuli. Three experimental studies were conducted. The first experiment identified perceptual boundaries for olfactory computation. In the second experiment, participants (N=25) were asked, across a fixed number of budgets (M=5), to identify what they perceived to be the best visual, acoustic and olfactory stimulus quality for a given computational budget. Results demonstrate that participants tend to prioritise visual quality compared to other sensory stimuli. However, as the budget size is increased, users prefer a balanced distribution of resources with an increased preference for having smell impulses in the VE. Based on the collected data, a quality prediction model is proposed and its accuracy is validated against previously unused budgets and an untested scenario in a third and final experiment. |
| Tasks | |
| Published | 2020-02-07 |
| URL | https://arxiv.org/abs/2002.02671v1 |
| https://arxiv.org/pdf/2002.02671v1.pdf | |
| PWC | https://paperswithcode.com/paper/audio-visual-olfactory-resource-allocation |
| Repo | |
| Framework | |
LAQP: Learning-based Approximate Query Processing
| Title | LAQP: Learning-based Approximate Query Processing |
| Authors | Meifan Zhang, Hongzhi Wang |
| Abstract | Querying on big data is a challenging task due to the rapid growth of data amount. Approximate query processing (AQP) is a way to meet the requirement of fast response. In this paper, we propose a learning-based AQP method called the LAQP. The LAQP builds an error model learned from the historical queries to predict the sampling-based estimation error of each new query. It makes a combination of the sampling-based AQP, the pre-computed aggregations and the learned error model to provide high-accurate query estimations with a small off-line sample. The experimental results indicate that our LAQP outperforms the sampling-based AQP, the pre-aggregation-based AQP and the most recent learning-based AQP method. |
| Tasks | |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02446v1 |
| https://arxiv.org/pdf/2003.02446v1.pdf | |
| PWC | https://paperswithcode.com/paper/laqp-learning-based-approximate-query |
| Repo | |
| Framework | |
Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence
| Title | Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence |
| Authors | Nicolas Donati, Abhishek Sharma, Maks Ovsjanikov |
| Abstract | We present a novel learning-based approach for computing correspondences between non-rigid 3D shapes. Unlike previous methods that either require extensive training data or operate on handcrafted input descriptors and thus generalize poorly across diverse datasets, our approach is both accurate and robust to changes in shape structure. Key to our method is a feature-extraction network that learns directly from raw shape geometry, combined with a novel regularized map extraction layer and loss, based on the functional map representation. We demonstrate through extensive experiments in challenging shape matching scenarios that our method can learn from less training data than existing supervised approaches and generalizes significantly better than current descriptor-based learning methods. Our source code is available at: https://github.com/LIX-shape-analysis/GeomFmaps. |
| Tasks | |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2003.14286v1 |
| https://arxiv.org/pdf/2003.14286v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-geometric-functional-maps-robust-feature |
| Repo | |
| Framework | |
Testing of Support Tools for Plagiarism Detection
| Title | Testing of Support Tools for Plagiarism Detection |
| Authors | Tomáš Foltýnek, Dita Dlabolová, Alla Anohina-Naumeca, Salim Razı, Július Kravjar, Laima Kamzola, Jean Guerrero-Dib, Özgür Çelik, Debora Weber-Wulff |
| Abstract | There is a general belief that software must be able to easily do things that humans find difficult. Since finding sources for plagiarism in a text is not an easy task, there is a wide-spread expectation that it must be simple for software to determine if a text is plagiarized or not. Software cannot determine plagiarism, but it can work as a support tool for identifying some text similarity that may constitute plagiarism. But how well do the various systems work? This paper reports on a collaborative test of 15 web-based text-matching systems that can be used when plagiarism is suspected. It was conducted by researchers from seven countries using test material in eight different languages, evaluating the effectiveness of the systems on single-source and multi-source documents. A usability examination was also performed. The sobering results show that although some systems can indeed help identify some plagiarized content, they clearly do not find all plagiarism and at times also identify non-plagiarized material as problematic. |
| Tasks | Text Matching |
| Published | 2020-02-11 |
| URL | https://arxiv.org/abs/2002.04279v1 |
| https://arxiv.org/pdf/2002.04279v1.pdf | |
| PWC | https://paperswithcode.com/paper/testing-of-support-tools-for-plagiarism |
| Repo | |
| Framework | |
