Paper Group ANR 403
Uncovering life-course patterns with causal discovery and survival analysis. Stochastic Linear Contextual Bandits with Diverse Contexts. Deep Audio-Visual Learning: A Survey. Visually Guided Self Supervised Learning of Speech Representations. Numerical Abstract Persuasion Argumentation for Expressing Concurrent Multi-Agent Negotiations. Boundary Gu …
Uncovering life-course patterns with causal discovery and survival analysis
| Title | Uncovering life-course patterns with causal discovery and survival analysis |
| Authors | Bojan Kostic, Romain Crastes dit Sourd, Stephane Hess, Joachim Scheiner, Christian Holz-Rau, Francisco C. Pereira |
| Abstract | We provide a novel approach and an exploratory study for modelling life event choices and occurrence from a probabilistic perspective through causal discovery and survival analysis. Our approach is formulated as a bi-level problem. In the upper level, we build the life events graph, using causal discovery tools. In the lower level, for the pairs of life events, time-to-event modelling through survival analysis is applied to model time-dependent transition probabilities. Several life events were analysed, such as getting married, buying a new car, child birth, home relocation and divorce, together with the socio-demographic attributes for survival modelling, some of which are age, nationality, number of children, number of cars and home ownership. The data originates from a survey conducted in Dortmund, Germany, with the questionnaire containing a series of retrospective questions about residential and employment biography, travel behaviour and holiday trips, as well as socio-economic characteristic. Although survival analysis has been used in the past to analyse life-course data, this is the first time that a bi-level model has been formulated. The inclusion of a causal discovery algorithm in the upper-level allows us to first identify causal relationships between life-course events and then understand the factors that might influence transition rates between events. This is very different from more classic choice models where causal relationships are subject to expert interpretations based on model results. |
| Tasks | Causal Discovery, Survival Analysis |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11399v1 |
| https://arxiv.org/pdf/2001.11399v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncovering-life-course-patterns-with-causal |
| Repo | |
| Framework | |
Stochastic Linear Contextual Bandits with Diverse Contexts
| Title | Stochastic Linear Contextual Bandits with Diverse Contexts |
| Authors | Weiqiang Wu, Jing Yang, Cong Shen |
| Abstract | In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits. As opposed to the previous view that contexts lead to more difficult bandit learning, we show that when the contexts are sufficiently diverse, the learner is able to utilize the information obtained during exploitation to shorten the exploration process, thus achieving reduced regret. We design the LinUCB-d algorithm, and propose a novel approach to analyze its regret performance. The main theoretical result is that under the diverse context assumption, the cumulative expected regret of LinUCB-d is bounded by a constant. As a by-product, our results improve the previous understanding of LinUCB and strengthen its performance guarantee. |
| Tasks | Multi-Armed Bandits |
| Published | 2020-03-05 |
| URL | https://arxiv.org/abs/2003.02681v1 |
| https://arxiv.org/pdf/2003.02681v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-linear-contextual-bandits-with |
| Repo | |
| Framework | |
Deep Audio-Visual Learning: A Survey
| Title | Deep Audio-Visual Learning: A Survey |
| Authors | Hao Zhu, Mandi Luo, Rui Wang, Aihua Zheng, Ran He |
| Abstract | Audio-visual learning, aimed at exploiting the relationship between audio and visual modalities, has drawn considerable attention since deep learning started to be used successfully. Researchers tend to leverage these two modalities either to improve the performance of previously considered single-modality tasks or to address new challenging problems. In this paper, we provide a comprehensive survey of recent audio-visual learning development. We divide the current audio-visual learning tasks into four different subfields: audio-visual separation and localization, audio-visual correspondence learning, audio-visual generation, and audio-visual representation learning. State-of-the-art methods as well as the remaining challenges of each subfield are further discussed. Finally, we summarize the commonly used datasets and performance metrics. |
| Tasks | Representation Learning |
| Published | 2020-01-14 |
| URL | https://arxiv.org/abs/2001.04758v1 |
| https://arxiv.org/pdf/2001.04758v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-audio-visual-learning-a-survey |
| Repo | |
| Framework | |
Visually Guided Self Supervised Learning of Speech Representations
| Title | Visually Guided Self Supervised Learning of Speech Representations |
| Authors | Abhinav Shukla, Konstantinos Vougioukas, Pingchuan Ma, Stavros Petridis, Maja Pantic |
| Abstract | Self supervised representation learning has recently attracted a lot of research interest for both the audio and visual modalities. However, most works typically focus on a particular modality or feature alone and there has been very limited work that studies the interaction between the two modalities for learning self supervised representations. We propose a framework for learning audio representations guided by the visual modality in the context of audiovisual speech. We employ a generative audio-to-video training scheme in which we animate a still image corresponding to a given audio clip and optimize the generated video to be as close as possible to the real video of the speech segment. Through this process, the audio encoder network learns useful speech representations that we evaluate on emotion recognition and speech recognition. We achieve state of the art results for emotion recognition and competitive results for speech recognition. This demonstrates the potential of visual supervision for learning audio representations as a novel way for self-supervised learning which has not been explored in the past. The proposed unsupervised audio features can leverage a virtually unlimited amount of training data of unlabelled audiovisual speech and have a large number of potentially promising applications. |
| Tasks | Emotion Recognition, Representation Learning, Speech Recognition |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.04316v2 |
| https://arxiv.org/pdf/2001.04316v2.pdf | |
| PWC | https://paperswithcode.com/paper/visually-guided-self-supervised-learning-of |
| Repo | |
| Framework | |
Numerical Abstract Persuasion Argumentation for Expressing Concurrent Multi-Agent Negotiations
| Title | Numerical Abstract Persuasion Argumentation for Expressing Concurrent Multi-Agent Negotiations |
| Authors | Ryuta Arisaka, Takayuki Ito |
| Abstract | A negotiation process by 2 agents e1 and e2 can be interleaved by another negotiation process between, say, e1 and e3. The interleaving may alter the resource allocation assumed at the inception of the first negotiation process. Existing proposals for argumentation-based negotiations have focused primarily on two-agent bilateral negotiations, but scarcely on the concurrency of multi-agent negotiations. To fill the gap, we present a novel argumentation theory, basing its development on abstract persuasion argumentation (which is an abstract argumentation formalism with a dynamic relation). Incorporating into it numerical information and a mechanism of handshakes among members of the dynamic relation, we show that the extended theory adapts well to concurrent multi-agent negotiations over scarce resources. |
| Tasks | Abstract Argumentation |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.08335v1 |
| https://arxiv.org/pdf/2001.08335v1.pdf | |
| PWC | https://paperswithcode.com/paper/numerical-abstract-persuasion-argumentation |
| Repo | |
| Framework | |
Boundary Guidance Hierarchical Network for Real-Time Tongue Segmentation
| Title | Boundary Guidance Hierarchical Network for Real-Time Tongue Segmentation |
| Authors | Xinyi Zeng, Qian Zhang, Jia Chen, Guixu Zhang, Aimin Zhou, Yiqin Wang |
| Abstract | Automated tongue image segmentation in tongue images is a challenging task for two reasons: 1) there are many pathological details on the tongue surface, which affect the extraction of the boundary; 2) the shapes of the tongues captured from various persons (with different diseases) are quite different. To deal with the challenge, a novel end-to-end Boundary Guidance Hierarchical Network (BGHNet) with a new hybrid loss is proposed in this paper. In the new approach, firstly Context Feature Encoder Module (CFEM) is built upon the bottomup pathway to confront with the shrinkage of the receptive field. Secondly, a novel hierarchical recurrent feature fusion module (HRFFM) is adopt to progressively and hierarchically refine object maps to recover image details by integrating local context information. Finally, the proposed hybrid loss in a four hierarchy-pixel, patch, map and boundary guides the network to effectively segment the tongue regions and accurate tongue boundaries. BGHNet is applied to a set of tongue images. The experimental results suggest that the proposed approach can achieve the latest tongue segmentation performance. And in the meantime, the lightweight network contains only 15.45M parameters and performs only 11.22GFLOPS. |
| Tasks | Semantic Segmentation |
| Published | 2020-03-14 |
| URL | https://arxiv.org/abs/2003.06529v1 |
| https://arxiv.org/pdf/2003.06529v1.pdf | |
| PWC | https://paperswithcode.com/paper/boundary-guidance-hierarchical-network-for |
| Repo | |
| Framework | |
Better Multi-class Probability Estimates for Small Data Sets
| Title | Better Multi-class Probability Estimates for Small Data Sets |
| Authors | Tuomo Alasalmi, Jaakko Suutala, Heli Koskimäki, Juha Röning |
| Abstract | Many classification applications require accurate probability estimates in addition to good class separation but often classifiers are designed focusing only on the latter. Calibration is the process of improving probability estimates by post-processing but commonly used calibration algorithms work poorly on small data sets and assume the classification task to be binary. Both of these restrictions limit their real-world applicability. Previously introduced Data Generation and Grouping algorithm alleviates the problem posed by small data sets and in this article, we will demonstrate that its application to multi-class problems is also possible which solves the other limitation. Our experiments show that calibration error can be decreased using the proposed approach and the additional computational cost is acceptable. |
| Tasks | Calibration |
| Published | 2020-01-30 |
| URL | https://arxiv.org/abs/2001.11242v1 |
| https://arxiv.org/pdf/2001.11242v1.pdf | |
| PWC | https://paperswithcode.com/paper/better-multi-class-probability-estimates-for |
| Repo | |
| Framework | |
Testing Monotonicity of Machine Learning Models
| Title | Testing Monotonicity of Machine Learning Models |
| Authors | Arnab Sharma, Heike Wehrheim |
| Abstract | Today, machine learning (ML) models are increasingly applied in decision making. This induces an urgent need for quality assurance of ML models with respect to (often domain-dependent) requirements. Monotonicity is one such requirement. It specifies a software as ‘learned’ by an ML algorithm to give an increasing prediction with the increase of some attribute values. While there exist multiple ML algorithms for ensuring monotonicity of the generated model, approaches for checking monotonicity, in particular of black-box models, are largely lacking. In this work, we propose verification-based testing of monotonicity, i.e., the formal computation of test inputs on a white-box model via verification technology, and the automatic inference of this approximating white-box model from the black-box model under test. On the white-box model, the space of test inputs can be systematically explored by a directed computation of test cases. The empirical evaluation on 90 black-box models shows verification-based testing can outperform adaptive random testing as well as property-based techniques with respect to effectiveness and efficiency. |
| Tasks | Decision Making |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12278v1 |
| https://arxiv.org/pdf/2002.12278v1.pdf | |
| PWC | https://paperswithcode.com/paper/testing-monotonicity-of-machine-learning |
| Repo | |
| Framework | |
Causal discovery of linear non-Gaussian acyclic models in the presence of latent confounders
| Title | Causal discovery of linear non-Gaussian acyclic models in the presence of latent confounders |
| Authors | Takashi Nicholas Maeda, Shohei Shimizu |
| Abstract | Causal discovery from data affected by latent confounders is an important and difficult challenge. Causal functional model-based approaches have not been used to present variables whose relationships are affected by latent confounders, while some constraint-based methods can present them. This paper proposes a causal functional model-based method called repetitive causal discovery (RCD) to discover the causal structure of observed variables affected by latent confounders. RCD repeats inferring the causal directions between a small number of observed variables and determines whether the relationships are affected by latent confounders. RCD finally produces a causal graph where a bi-directed arrow indicates the pair of variables that have the same latent confounders, and a directed arrow indicates the causal direction of a pair of variables that are not affected by the same latent confounder. The results of experimental validation using simulated data and real-world data confirmed that RCD is effective in identifying latent confounders and causal directions between observed variables. |
| Tasks | Causal Discovery |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.04197v2 |
| https://arxiv.org/pdf/2001.04197v2.pdf | |
| PWC | https://paperswithcode.com/paper/rcd-repetitive-causal-discovery-of-linear-non |
| Repo | |
| Framework | |
MOEA/D with Random Partial Update Strategy
| Title | MOEA/D with Random Partial Update Strategy |
| Authors | Yuri Lavinas, Claus Aranha, Marcelo Ladeira, Felipe Campelo |
| Abstract | Recent studies on resource allocation suggest that some subproblems are more important than others in the context of the MOEA/D, and that focusing on the most relevant ones can consistently improve the performance of that algorithm. These studies share the common characteristic of updating only a fraction of the population at any given iteration of the algorithm. In this work we investigate a new, simpler partial update strategy, in which a random subset of solutions is selected at every iteration. The performance of the MOEA/D using this new resource allocation approach is compared experimentally against that of the standard MOEA/D-DE and the MOEA/D with relative improvement-based resource allocation. The results indicate that using the MOEA/D with this new partial update strategy results in improved HV and IGD values, and a much higher proportion of non-dominated solutions, particularly as the number of updated solutions at every iteration is reduced. |
| Tasks | |
| Published | 2020-01-20 |
| URL | https://arxiv.org/abs/2001.06980v1 |
| https://arxiv.org/pdf/2001.06980v1.pdf | |
| PWC | https://paperswithcode.com/paper/moead-with-random-partial-update-strategy |
| Repo | |
| Framework | |
A survey of bias in Machine Learning through the prism of Statistical Parity for the Adult Data Set
| Title | A survey of bias in Machine Learning through the prism of Statistical Parity for the Adult Data Set |
| Authors | Philippe Besse, Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes, Laurent Risser |
| Abstract | Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world. A critical question then recently arised among the population: Do algorithmic decisions convey any type of discrimination against specific groups of population or minorities? In this paper, we show the importance of understanding how a bias can be introduced into automatic decisions. We first present a mathematical framework for the fair learning problem, specifically in the binary classification setting. We then propose to quantify the presence of bias by using the standard Disparate Impact index on the real and well-known Adult income data set. Finally, we check the performance of different approaches aiming to reduce the bias in binary classification outcomes. Importantly, we show that some intuitive methods are ineffective. This sheds light on the fact trying to make fair machine learning models may be a particularly challenging task, in particular when the training observations contain a bias. |
| Tasks | |
| Published | 2020-03-31 |
| URL | https://arxiv.org/abs/2003.14263v1 |
| https://arxiv.org/pdf/2003.14263v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-bias-in-machine-learning-through |
| Repo | |
| Framework | |
A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via $f$-Divergences
| Title | A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via $f$-Divergences |
| Authors | Shahab Asoodeh, Jiachun Liao, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar |
| Abstract | We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R'enyi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie the approximate and the R'enyi variations of differential privacy. We apply our result to the moments accountant framework for characterizing privacy guarantees of stochastic gradient descent. When compared to the state-of-the-art, our bounds may lead to about 100 more stochastic gradient descent iterations for training deep learning models for the same privacy budget. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.05990v1 |
| https://arxiv.org/pdf/2001.05990v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-better-bound-gives-a-hundred-rounds |
| Repo | |
| Framework | |
Interactive Neural Style Transfer with Artists
| Title | Interactive Neural Style Transfer with Artists |
| Authors | Thomas Kerdreux, Louis Thiry, Erwan Kerdreux |
| Abstract | We present interactive painting processes in which a painter and various neural style transfer algorithms interact on a real canvas. Understanding what these algorithms’ outputs achieve is then paramount to describe the creative agency in our interactive experiments. We gather a set of paired painting-pictures images and present a new evaluation methodology based on the predictivity of neural style transfer algorithms. We point some algorithms’ instabilities and show that they can be used to enlarge the diversity and pleasing oddity of the images synthesized by the numerous existing neural style transfer algorithms. This diversity of images was perceived as a source of inspiration for human painters, portraying the machine as a computational catalyst. |
| Tasks | Style Transfer |
| Published | 2020-03-14 |
| URL | https://arxiv.org/abs/2003.06659v1 |
| https://arxiv.org/pdf/2003.06659v1.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-neural-style-transfer-with |
| Repo | |
| Framework | |
Black-box Methods for Restoring Monotonicity
| Title | Black-box Methods for Restoring Monotonicity |
| Authors | Evangelia Gergatsouli, Brendan Lucier, Christos Tzamos |
| Abstract | In many practical applications, heuristic or approximation algorithms are used to efficiently solve the task at hand. However their solutions frequently do not satisfy natural monotonicity properties of optimal solutions. In this work we develop algorithms that are able to restore monotonicity in the parameters of interest. Specifically, given oracle access to a (possibly non-monotone) multi-dimensional real-valued function $f$, we provide an algorithm that restores monotonicity while degrading the expected value of the function by at most $\varepsilon$. The number of queries required is at most logarithmic in $1/\varepsilon$ and exponential in the number of parameters. We also give a lower bound showing that this exponential dependence is necessary. Finally, we obtain improved query complexity bounds for restoring the weaker property of $k$-marginal monotonicity. Under this property, every $k$-dimensional projection of the function $f$ is required to be monotone. The query complexity we obtain only scales exponentially with $k$. |
| Tasks | |
| Published | 2020-03-21 |
| URL | https://arxiv.org/abs/2003.09554v1 |
| https://arxiv.org/pdf/2003.09554v1.pdf | |
| PWC | https://paperswithcode.com/paper/black-box-methods-for-restoring-monotonicity |
| Repo | |
| Framework | |
Content Based Singing Voice Extraction From a Musical Mixture
| Title | Content Based Singing Voice Extraction From a Musical Mixture |
| Authors | Pritish Chandna, Merlijn Blaauw, Jordi Bonada, Emilia Gomez |
| Abstract | We present a deep learning based methodology for extracting the singing voice signal from a musical mixture based on the underlying linguistic content. Our model follows an encoder decoder architecture and takes as input the magnitude component of the spectrogram of a musical mixture with vocals. The encoder part of the model is trained via knowledge distillation using a teacher network to learn a content embedding, which is decoded to generate the corresponding vocoder features. Using this methodology, we are able to extract the unprocessed raw vocal signal from the mixture even for a processed mixture dataset with singers not seen during training. While the nature of our system makes it incongruous with traditional objective evaluation metrics, we use subjective evaluation via listening tests to compare the methodology to state-of-the-art deep learning based source separation algorithms. We also provide sound examples and source code for reproducibility. |
| Tasks | |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.04933v2 |
| https://arxiv.org/pdf/2002.04933v2.pdf | |
| PWC | https://paperswithcode.com/paper/content-based-singing-voice-extraction-from-a |
| Repo | |
| Framework | |
