Paper Group ANR 1107
Barcodes as summary of objective function’s topology. Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond. Artificial Intelligence: the global landscape of ethics guidelines. Investigating Writing Style Development in High School. Developing Computational Models of Social Assistance to Guide Socially Assistive Rob …
Barcodes as summary of objective function’s topology
| Title | Barcodes as summary of objective function’s topology |
| Authors | Serguei Barannikov, Alexander Korotin, Dmitry Oganesyan, Daniil Emtsev, Evgeny Burnaev |
| Abstract | We apply the canonical forms (barcodes) of gradient Morse complexes to explore topology of loss surfaces. We present a new algorithm for calculations of the objective function’s barcodes of minima. Our experiments confirm two principal observations: 1) the barcodes of minima are located in a small lower part of the range of values of loss function of neural networks, 2) an increase of the neural network’s depth brings down the minima’s barcodes. This has natural implications for the neural network’s learning and generalization ability. |
| Tasks | |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1912.00043v1 |
| https://arxiv.org/pdf/1912.00043v1.pdf | |
| PWC | https://paperswithcode.com/paper/barcodes-as-summary-of-objective-functions-1 |
| Repo | |
| Framework | |
Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond
| Title | Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond |
| Authors | Arindam Banerjee, Qilong Gu, Vidyashankar Sivakumar, Zhiwei Steven Wu |
| Abstract | Several important families of computational and statistical results in machine learning and randomized algorithms rely on uniform bounds on quadratic forms of random vectors or matrices. Such results include the Johnson-Lindenstrauss (J-L) Lemma, the Restricted Isometry Property (RIP), randomized sketching algorithms, and approximate linear algebra. The existing results critically depend on statistical independence, e.g., independent entries for random vectors, independent rows for random matrices, etc., which prevent their usage in dependent or adaptive modeling settings. In this paper, we show that such independence is in fact not needed for such results which continue to hold under fairly general dependence structures. In particular, we present uniform bounds on random quadratic forms of stochastic processes which are conditionally independent and sub-Gaussian given another (latent) process. Our setup allows general dependencies of the stochastic process on the history of the latent process and the latent process to be influenced by realizations of the stochastic process. The results are thus applicable to adaptive modeling settings and also allows for sequential design of random vectors and matrices. We also discuss stochastic process based forms of J-L, RIP, and sketching, to illustrate the generality of the results. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04930v2 |
| https://arxiv.org/pdf/1910.04930v2.pdf | |
| PWC | https://paperswithcode.com/paper/random-quadratic-forms-with-dependence |
| Repo | |
| Framework | |
Artificial Intelligence: the global landscape of ethics guidelines
| Title | Artificial Intelligence: the global landscape of ethics guidelines |
| Authors | Anna Jobin, Marcello Ienca, Effy Vayena |
| Abstract | In the last five years, private companies, research institutions as well as public sector organisations have issued principles and guidelines for ethical AI, yet there is debate about both what constitutes “ethical AI” and which ethical requirements, technical standards and best practices are needed for its realization. To investigate whether a global agreement on these questions is emerging, we mapped and analyzed the current corpus of principles and guidelines on ethical AI. Our results reveal a global convergence emerging around five ethical principles (transparency, justice and fairness, non-maleficence, responsibility and privacy), with substantive divergence in relation to how these principles are interpreted; why they are deemed important; what issue, domain or actors they pertain to; and how they should be implemented. Our findings highlight the importance of integrating guideline-development efforts with substantive ethical analysis and adequate implementation strategies. |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.11668v1 |
| https://arxiv.org/pdf/1906.11668v1.pdf | |
| PWC | https://paperswithcode.com/paper/artificial-intelligence-the-global-landscape |
| Repo | |
| Framework | |
Investigating Writing Style Development in High School
| Title | Investigating Writing Style Development in High School |
| Authors | Stephan Lorenzen, Niklas Hjuler, Stephen Alstrup |
| Abstract | In this paper we do the first large scale analysis of writing style development among Danish high school students. More than 10K students with more than 100K essays are analyzed. Writing style itself is often studied in the natural language processing community, but usually with the goal of verifying authorship, assessing quality or popularity, or other kinds of predictions. In this work, we analyze writing style changes over time, with the goal of detecting global development trends among students, and identifying at-risk students. We train a Siamese neural network to compute the similarity between two texts. Using this similarity measure, a student’s newer essays are compared to their first essays, and a writing style development profile is constructed for the student. We cluster these student profiles and analyze the resulting clusters in order to detect general development patterns. We evaluate clusters with respect to writing style quality indicators, and identify optimal clusters, showing significant improvement in writing style, while also observing suboptimal clusters, exhibiting periods of limited development and even setbacks. Furthermore, we identify general development trends between high school students, showing that as students progress through high school, their writing style deviates, leaving students less similar when they finish high school, than when they start. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.03072v1 |
| https://arxiv.org/pdf/1906.03072v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-writing-style-development-in |
| Repo | |
| Framework | |
Developing Computational Models of Social Assistance to Guide Socially Assistive Robots
| Title | Developing Computational Models of Social Assistance to Guide Socially Assistive Robots |
| Authors | Jason R. Wilson, Seongsik Kim, Ulyana Kurylo, Joseph Cummings, Eshan Tarneja |
| Abstract | While there are many examples in which robots provide social assistance, a lack of theory on how the robots should decide how to assist impedes progress in realizing these technologies. To address this deficiency, we propose a pair of computational models to guide a robot as it provides social assistance. The model of social autonomy helps a robot select an appropriate assistance that will help with the task at hand while also maintaining the autonomy of the person being assisted. The model of social alliance describes how a to determine whether the robot and the person being assisted are cooperatively working towards the same goal. Each of these models are rooted in social reasoning between people, and we describe here our ongoing work to adapt this social reasoning to human-robot interactions. |
| Tasks | |
| Published | 2019-09-14 |
| URL | https://arxiv.org/abs/1909.06510v1 |
| https://arxiv.org/pdf/1909.06510v1.pdf | |
| PWC | https://paperswithcode.com/paper/developing-computational-models-of-social |
| Repo | |
| Framework | |
Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification
| Title | Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification |
| Authors | Xiaochen Hou, Jing Huang, Guangtao Wang, Kevin Huang, Xiaodong He, Bowen Zhou |
| Abstract | Aspect-level sentiment classification aims to identify the sentiment polarity towards a specific aspect term in a sentence. Most current approaches mainly consider the semantic information by utilizing attention mechanisms to capture the interactions between the context and the aspect term. In this paper, we propose to employ graph convolutional networks (GCNs) on the dependency tree to learn syntax-aware representations of aspect terms. GCNs often show the best performance with two layers, and deeper GCNs do not bring additional gain due to over-smoothing problem. However, in some cases, important context words cannot be reached within two hops on the dependency tree. Therefore we design a selective attention based GCN block (SA-GCN) to find the most important context words, and directly aggregate these information into the aspect-term representation. We conduct experiments on the SemEval 2014 Task 4 datasets. Our experimental results show that our model outperforms the current state-of-the-art. |
| Tasks | Sentiment Analysis |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.10857v1 |
| https://arxiv.org/pdf/1910.10857v1.pdf | |
| PWC | https://paperswithcode.com/paper/selective-attention-based-graph-convolutional |
| Repo | |
| Framework | |
Survey on Deep Neural Networks in Speech and Vision Systems
| Title | Survey on Deep Neural Networks in Speech and Vision Systems |
| Authors | Mahbubul Alam, Manar D. Samad, Lasitha Vidyaratne, Alexander Glandon, Khan M. Iftekharuddin |
| Abstract | This survey presents a review of state-of-the-art deep neural network architectures, algorithms, and systems in vision and speech applications. Recent advances in deep artificial neural network algorithms and architectures have spurred rapid innovation and development of intelligent vision and speech systems. With availability of vast amounts of sensor data and cloud computing for processing and training of deep neural networks, and with increased sophistication in mobile and embedded technology, the next-generation intelligent systems are poised to revolutionize personal and commercial computing. This survey begins by providing background and evolution of some of the most successful deep learning models for intelligent vision and speech systems to date. An overview of large-scale industrial research and development efforts is provided to emphasize future trends and prospects of intelligent vision and speech systems. Robust and efficient intelligent systems demand low-latency and high fidelity in resource-constrained hardware platforms such as mobile devices, robots, and automobiles. Therefore, this survey also provides a summary of key challenges and recent successes in running deep neural networks on hardware-restricted platforms, i.e. within limited memory, battery life, and processing capabilities. Finally, emerging applications of vision and speech across disciplines such as affective computing, intelligent transportation, and precision medicine are discussed. To our knowledge, this paper provides one of the most comprehensive surveys on the latest developments in intelligent vision and speech applications from the perspectives of both software and hardware systems. Many of these emerging technologies using deep neural networks show tremendous promise to revolutionize research and development for future vision and speech systems. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.07656v2 |
| https://arxiv.org/pdf/1908.07656v2.pdf | |
| PWC | https://paperswithcode.com/paper/190807656 |
| Repo | |
| Framework | |
Going Negative Online? – A Study of Negative Advertising on Social Media
| Title | Going Negative Online? – A Study of Negative Advertising on Social Media |
| Authors | Hongtao Liu |
| Abstract | A growing number of empirical studies suggest that negative advertising is effective in campaigning, while the mechanisms are rarely mentioned. With the scandal of Cambridge Analytica and Russian intervention behind the Brexit and the 2016 presidential election, people have become aware of the political ads on social media and have pressured congress to restrict political advertising on social media. Following the related legislation, social media companies began disclosing their political ads archive for transparency during the summer of 2018 when the midterm election campaign was just beginning. This research collects the data of the related political ads in the context of the U.S. midterm elections since August to study the overall pattern of political ads on social media and uses sets of machine learning methods to conduct sentiment analysis on these ads to classify the negative ads. A novel approach is applied that uses AI image recognition to study the image data. Through data visualization, this research shows that negative advertising is still the minority, Republican advertisers and third party organizations are more likely to engage in negative advertising than their counterparts. Based on ordinal regressions, this study finds that anger evoked information-seeking is one of the main mechanisms causing negative ads to be more engaging and effective rather than the negative bias theory. Overall, this study provides a unique understanding of political advertising on social media by applying innovative data science methods. Further studies can extend the findings, methods, and datasets in this study, and several suggestions are given for future research. |
| Tasks | Sentiment Analysis |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1911.05497v1 |
| https://arxiv.org/pdf/1911.05497v1.pdf | |
| PWC | https://paperswithcode.com/paper/going-negative-online-a-study-of-negative |
| Repo | |
| Framework | |
An Intelligent Data Analysis for Hotel Recommendation Systems using Machine Learning
| Title | An Intelligent Data Analysis for Hotel Recommendation Systems using Machine Learning |
| Authors | Bushra Ramzan, Imran Sarwar Bajwa, Noreen Jamil, Farhaan Mirza |
| Abstract | This paper presents an intelligent approach to handle heterogeneous and large-sized data using machine learning to generate true recommendations for the future customers. The Collaborative Filtering (CF) approach is one of the most popular techniques of the RS to generate recommendations. We have proposed a novel CF recommendation approach in which opinion based sentiment analysis is used to achieve hotel feature matrix by polarity identification. Our approach combines lexical analysis, syntax analysis and semantic analysis to understand sentiment towards hotel features and the profiling of guest type (solo, family, couple etc). The proposed system recommends hotels based on the hotel features and guest type as additional information for personalized recommendation. The developed system not only has the ability to handle heterogeneous data using big data Hadoop platform but it also recommend hotel class based on guest type using fuzzy rules. Different experiments are performed over the real world dataset obtained from two hotel websites. Moreover, the values of precision and recall and F-measure have been calculated and results are discussed in terms of improved accuracy and response time, significantly better than the traditional approaches. |
| Tasks | Lexical Analysis, Recommendation Systems, Sentiment Analysis |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06669v1 |
| https://arxiv.org/pdf/1910.06669v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-intelligent-data-analysis-for-hotel |
| Repo | |
| Framework | |
Efficient Computation of Probabilistic Dominance in Robust Multi-Objective Optimization
| Title | Efficient Computation of Probabilistic Dominance in Robust Multi-Objective Optimization |
| Authors | Faramarz Khosravi, Alexander Raß, Jürgen Teich |
| Abstract | Real-world problems typically require the simultaneous optimization of several, often conflicting objectives. Many of these multi-objective optimization problems are characterized by wide ranges of uncertainties in their decision variables or objective functions, which further increases the complexity of optimization. To cope with such uncertainties, robust optimization is widely studied aiming to distinguish candidate solutions with uncertain objectives specified by confidence intervals, probability distributions or sampled data. However, existing techniques mostly either fail to consider the actual distributions or assume uncertainty as instances of uniform or Gaussian distributions. This paper introduces an empirical approach that enables an efficient comparison of candidate solutions with uncertain objectives that can follow arbitrary distributions. Given two candidate solutions under comparison, this operator calculates the probability that one solution dominates the other in terms of each uncertain objective. It can substitute for the standard comparison operator of existing optimization techniques such as evolutionary algorithms to enable discovering robust solutions to problems with multiple uncertain objectives. This paper also proposes to incorporate various uncertainties in well-known multi-objective problems to provide a benchmark for evaluating uncertainty-aware optimization techniques. The proposed comparison operator and benchmark suite are integrated into an existing optimization tool that features a selection of multi-objective optimization problems and algorithms. Experiments show that in comparison with existing techniques, the proposed approach achieves higher optimization quality at lower overheads. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08413v1 |
| https://arxiv.org/pdf/1910.08413v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-computation-of-probabilistic |
| Repo | |
| Framework | |
On the use of Pairwise Distance Learning for Brain Signal Classification with Limited Observations
| Title | On the use of Pairwise Distance Learning for Brain Signal Classification with Limited Observations |
| Authors | David Calhas, Enrique Romero, Rui Henriques |
| Abstract | The increasing access to brain signal data using electroencephalography creates new opportunities to study electrophysiological brain activity and perform ambulatory diagnoses of neuronal diseases. This work proposes a pairwise distance learning approach for Schizophrenia classification relying on the spectral properties of the signal. Given the limited number of observations (i.e. the case and/or control individuals) in clinical trials, we propose a Siamese neural network architecture to learn a discriminative feature space from pairwise combinations of observations per channel. In this way, the multivariate order of the signal is used as a form of data augmentation, further supporting the network generalization ability. Convolutional layers with parameters learned under a cosine contrastive loss are proposed to adequately explore spectral images derived from the brain signal. Results on a case-control population show that the features extracted using the proposed neural network lead to an improved Schizophrenia diagnosis (+10pp in accuracy and sensitivity) against spectral features, thus suggesting the existence of non-trivial, discriminative electrophysiological brain patterns. |
| Tasks | Data Augmentation |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02076v2 |
| https://arxiv.org/pdf/1906.02076v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-use-of-pairwise-distance-learning-for |
| Repo | |
| Framework | |
SmokEng: Towards Fine-grained Classification of Tobacco-related Social Media Text
| Title | SmokEng: Towards Fine-grained Classification of Tobacco-related Social Media Text |
| Authors | Kartikey Pant, Venkata Himakar Yanamandra, Alok Debnath, Radhika Mamidi |
| Abstract | Contemporary datasets on tobacco consumption focus on one of two topics, either public health mentions and disease surveillance, or sentiment analysis on topical tobacco products and services. However, two primary considerations are not accounted for, the language of the demographic affected and a combination of the topics mentioned above in a fine-grained classification mechanism. In this paper, we create a dataset of 3144 tweets, which are selected based on the presence of colloquial slang related to smoking and analyze it based on the semantics of the tweet. Each class is created and annotated based on the content of the tweets such that further hierarchical methods can be easily applied. Further, we prove the efficacy of standard text classification methods on this dataset, by designing experiments which do both binary as well as multi-class classification. Our experiments tackle the identification of either a specific topic (such as tobacco product promotion), a general mention (cigarettes and related products) or a more fine-grained classification. This methodology paves the way for further analysis, such as understanding sentiment or style, which makes this dataset a vital contribution to both disease surveillance and tobacco use research. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.05598v1 |
| https://arxiv.org/pdf/1910.05598v1.pdf | |
| PWC | https://paperswithcode.com/paper/smokeng-towards-fine-grained-classification |
| Repo | |
| Framework | |
Certified Reinforcement Learning with Logic Guidance
| Title | Certified Reinforcement Learning with Logic Guidance |
| Authors | Mohammadhosein Hasanbeig, Alessandro Abate, Daniel Kroening |
| Abstract | This paper proposes the first model-free Reinforcement Learning (RL) framework to synthesise policies for unknown, and continuous-state Markov Decision Processes (MDPs), such that a given linear temporal property is satisfied. We convert the given property into a Limit Deterministic Buchi Automaton (LDBA), namely a finite-state machine expressing the property. Exploiting the structure of the LDBA, we shape a synchronous reward function on-the-fly, so that an RL algorithm can synthesise a policy resulting in traces that probabilistically satisfy the linear temporal property. This probability (certificate) is also calculated in parallel with policy learning when the state space of the MDP is finite: as such, the RL algorithm produces a policy that is certified with respect to the property. Under the assumption of finite state space, theoretical guarantees are provided on the convergence of the RL algorithm to an optimal policy, maximising the above probability. We also show that our method produces ‘‘best available’’ control policies when the logical property cannot be satisfied. In the general case of a continuous state space, we propose a neural network architecture for RL and we empirically show that the algorithm finds satisfying policies, if there exist such policies. The performance of the proposed framework is evaluated via a set of numerical examples and benchmarks, where we observe an improvement of one order of magnitude in the number of iterations required for the policy synthesis, compared to existing approaches whenever available. |
| Tasks | |
| Published | 2019-02-02 |
| URL | https://arxiv.org/abs/1902.00778v3 |
| https://arxiv.org/pdf/1902.00778v3.pdf | |
| PWC | https://paperswithcode.com/paper/certified-reinforcement-learning-with-logic |
| Repo | |
| Framework | |
Convergence of Learning Dynamics in Stackelberg Games
| Title | Convergence of Learning Dynamics in Stackelberg Games |
| Authors | Tanner Fiez, Benjamin Chasnov, Lillian J. Ratliff |
| Abstract | This paper investigates the convergence of learning dynamics in Stackelberg games. In the class of games we consider, there is a hierarchical game being played between a leader and a follower with continuous action spaces. We establish a number of connections between the Nash and Stackelberg equilibrium concepts and characterize conditions under which attracting critical points of simultaneous gradient descent are Stackelberg equilibria in zero-sum games. Moreover, we show that the only stable critical points of the Stackelberg gradient dynamics are Stackelberg equilibria in zero-sum games. Using this insight, we develop a gradient-based update for the leader while the follower employs a best response strategy for which each stable critical point is guaranteed to be a Stackelberg equilibrium in zero-sum games. As a result, the learning rule provably converges to a Stackelberg equilibria given an initialization in the region of attraction of a stable critical point. We then consider a follower employing a gradient-play update rule instead of a best response strategy and propose a two-timescale algorithm with similar asymptotic convergence guarantees. For this algorithm, we also provide finite-time high probability bounds for local convergence to a neighborhood of a stable Stackelberg equilibrium in general-sum games. Finally, we present extensive numerical results that validate our theory, provide insights into the optimization landscape of generative adversarial networks, and demonstrate that the learning dynamics we propose can effectively train generative adversarial networks. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01217v3 |
| https://arxiv.org/pdf/1906.01217v3.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-of-learning-dynamics-in-1 |
| Repo | |
| Framework | |
Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information
| Title | Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information |
| Authors | Qiu Ran, Yankai Lin, Peng Li, Jie Zhou |
| Abstract | Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compared to autoregressive neural machine translation models due to the enormous decoding space. To address this problem, we propose a novel NAT framework named ReorderNAT which explicitly models the reordering information in the decoding procedure. We further introduce deterministic and non-deterministic decoding strategies that utilize reordering information to narrow the decoding search space in our proposed ReorderNAT. Experimental results on various widely-used datasets show that our proposed model achieves better performance compared to existing NAT models, and even achieves comparable translation quality as autoregressive translation models with a significant speedup. |
| Tasks | Machine Translation |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02215v1 |
| https://arxiv.org/pdf/1911.02215v1.pdf | |
| PWC | https://paperswithcode.com/paper/guiding-non-autoregressive-neural-machine |
| Repo | |
| Framework | |
