Paper Group ANR 189
Why Is My Classifier Discriminatory?. Nudging Neural Conversational Model with Domain Knowledge. HAMLET: Hierarchical Harmonic Filters for Learning Tracts from Diffusion MRI. OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding. A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symm …
Why Is My Classifier Discriminatory?
| Title | Why Is My Classifier Discriminatory? |
| Authors | Irene Chen, Fredrik D. Johansson, David Sontag |
| Abstract | Recent attempts to achieve fairness in predictive models focus on the balance between fairness and accuracy. In sensitive applications such as healthcare or criminal justice, this trade-off is often undesirable as any increase in prediction error could have devastating consequences. In this work, we argue that the fairness of predictions should be evaluated in context of the data, and that unfairness induced by inadequate samples sizes or unmeasured predictive variables should be addressed through data collection, rather than by constraining the model. We decompose cost-based metrics of discrimination into bias, variance, and noise, and propose actions aimed at estimating and reducing each term. Finally, we perform case-studies on prediction of income, mortality, and review ratings, confirming the value of this analysis. We find that data collection is often a means to reduce discrimination without sacrificing accuracy. |
| Tasks | |
| Published | 2018-05-30 |
| URL | http://arxiv.org/abs/1805.12002v2 |
| http://arxiv.org/pdf/1805.12002v2.pdf | |
| PWC | https://paperswithcode.com/paper/why-is-my-classifier-discriminatory |
| Repo | |
| Framework | |
Nudging Neural Conversational Model with Domain Knowledge
| Title | Nudging Neural Conversational Model with Domain Knowledge |
| Authors | Sungjin Lee |
| Abstract | Neural conversation models are attractive because one can train a model directly on dialog examples with minimal labeling. With a small amount of data, however, they often fail to generalize over test data since they tend to capture spurious features instead of semantically meaningful domain knowledge. To address this issue, we propose a novel approach that allows any human teachers to transfer their domain knowledge to the conversation model in the form of natural language rules. We tested our method with three different dialog datasets. The improved performance across all domains demonstrates the efficacy of our proposed method. |
| Tasks | |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06630v1 |
| http://arxiv.org/pdf/1811.06630v1.pdf | |
| PWC | https://paperswithcode.com/paper/nudging-neural-conversational-model-with |
| Repo | |
| Framework | |
HAMLET: Hierarchical Harmonic Filters for Learning Tracts from Diffusion MRI
| Title | HAMLET: Hierarchical Harmonic Filters for Learning Tracts from Diffusion MRI |
| Authors | Marco Reisert, Volker A. Coenen, Christoph Kaller, Karl Egger, Henrik Skibbe |
| Abstract | In this work we propose HAMLET, a novel tract learning algorithm, which, after training, maps raw diffusion weighted MRI directly onto an image which simultaneously indicates tract direction and tract presence. The automatic learning of fiber tracts based on diffusion MRI data is a rather new idea, which tries to overcome limitations of atlas-based techniques. HAMLET takes a such an approach. Unlike the current trend in machine learning, HAMLET has only a small number of free parameters HAMLET is based on spherical tensor algebra which allows a translation and rotation covariant treatment of the problem. HAMLET is based on a repeated application of convolutions and non-linearities, which all respect the rotation covariance. The intrinsic treatment of such basic image transformations in HAMLET allows the training and generalization of the algorithm without any additional data augmentation. We demonstrate the performance of our approach for twelve prominent bundles, and show that the obtained tract estimates are robust and reliable. It is also shown that the learned models are portable from one sequence to another. |
| Tasks | Data Augmentation |
| Published | 2018-07-03 |
| URL | http://arxiv.org/abs/1807.01068v1 |
| http://arxiv.org/pdf/1807.01068v1.pdf | |
| PWC | https://paperswithcode.com/paper/hamlet-hierarchical-harmonic-filters-for |
| Repo | |
| Framework | |
OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding
| Title | OneNet: Joint Domain, Intent, Slot Prediction for Spoken Language Understanding |
| Authors | Young-Bum Kim, Sungjin Lee, Karl Stratos |
| Abstract | In practice, most spoken language understanding systems process user input in a pipelined manner; first domain is predicted, then intent and semantic slots are inferred according to the semantic frames of the predicted domain. The pipeline approach, however, has some disadvantages: error propagation and lack of information sharing. To address these issues, we present a unified neural network that jointly performs domain, intent, and slot predictions. Our approach adopts a principled architecture for multitask learning to fold in the state-of-the-art models for each task. With a few more ingredients, e.g. orthography-sensitive input encoding and curriculum training, our model delivered significant improvements in all three tasks across all domains over strong baselines, including one using oracle prediction for domain detection, on real user data of a commercial personal assistant. |
| Tasks | Spoken Language Understanding |
| Published | 2018-01-16 |
| URL | http://arxiv.org/abs/1801.05149v1 |
| http://arxiv.org/pdf/1801.05149v1.pdf | |
| PWC | https://paperswithcode.com/paper/onenet-joint-domain-intent-slot-prediction |
| Repo | |
| Framework | |
A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rule
| Title | A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rule |
| Authors | Yunzhe Hao, Xuhui Huang, Meng Dong, Bo Xu |
| Abstract | Spiking neural networks (SNNs) possess energy-efficient potential due to event-based computation. However, supervised training of SNNs remains a challenge as spike activities are non-differentiable. Previous SNNs training methods can be generally categorized into two basic classes, i.e., backpropagation-like training methods and plasticity-based learning methods. The former methods are dependent on energy-inefficient real-valued computation and non-local transmission, as also required in artificial neural networks (ANNs), whereas the latter are either considered to be biologically implausible or exhibit poor performance. Hence, biologically plausible (bio-plausible) high-performance supervised learning (SL) methods for SNNs remain deficient. In this paper, we proposed a novel bio-plausible SNN model for SL based on the symmetric spike-timing dependent plasticity (sym-STDP) rule found in neuroscience. By combining the sym-STDP rule with bio-plausible synaptic scaling and intrinsic plasticity of the dynamic threshold, our SNN model implemented SL well and achieved good performance in the benchmark recognition task (MNIST dataset). To reveal the underlying mechanism of our SL model, we visualized both layer-based activities and synaptic weights using the t-distributed stochastic neighbor embedding (t-SNE) method after training and found that they were well clustered, thereby demonstrating excellent classification ability. Furthermore, to verify the robustness of our model, we trained it on another more realistic dataset (Fashion-MNIST), which also showed good performance. As the learning rules were bio-plausible and based purely on local spike events, our model could be easily applied to neuromorphic hardware for online training and may be helpful for understanding SL information processing at the synaptic level in biological neural systems. |
| Tasks | |
| Published | 2018-12-17 |
| URL | https://arxiv.org/abs/1812.06574v3 |
| https://arxiv.org/pdf/1812.06574v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-biologically-plausible-supervised-learning |
| Repo | |
| Framework | |
Computational Anatomy for Multi-Organ Analysis in Medical Imaging: A Review
| Title | Computational Anatomy for Multi-Organ Analysis in Medical Imaging: A Review |
| Authors | Juan J. Cerrolaza, Mirella Lopez-Picazo, Ludovic Humbert, Yoshinobu Sato, Daniel Rueckert, Miguel Angel Gonzalez Ballester, Marius George Linguraru |
| Abstract | The medical image analysis field has traditionally been focused on the development of organ-, and disease-specific methods. Recently, the interest in the development of more 20 comprehensive computational anatomical models has grown, leading to the creation of multi-organ models. Multi-organ approaches, unlike traditional organ-specific strategies, incorporate inter-organ relations into the model, thus leading to a more accurate representation of the complex human anatomy. Inter-organ relations are not only spatial, but also functional and physiological. Over the years, the strategies 25 proposed to efficiently model multi-organ structures have evolved from the simple global modeling, to more sophisticated approaches such as sequential, hierarchical, or machine learning-based models. In this paper, we present a review of the state of the art on multi-organ analysis and associated computation anatomy methodology. The manuscript follows a methodology-based classification of the different techniques 30 available for the analysis of multi-organs and multi-anatomical structures, from techniques using point distribution models to the most recent deep learning-based approaches. With more than 300 papers included in this review, we reflect on the trends and challenges of the field of computational anatomy, the particularities of each anatomical region, and the potential of multi-organ analysis to increase the impact of 35 medical imaging applications on the future of healthcare. |
| Tasks | |
| Published | 2018-12-20 |
| URL | http://arxiv.org/abs/1812.08577v1 |
| http://arxiv.org/pdf/1812.08577v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-anatomy-for-multi-organ |
| Repo | |
| Framework | |
Exactly Robust Kernel Principal Component Analysis
| Title | Exactly Robust Kernel Principal Component Analysis |
| Authors | Jicong Fan, Tommy W. S. Chow |
| Abstract | Robust principal component analysis (RPCA) can recover low-rank matrices when they are corrupted by sparse noises. In practice, many matrices are, however, of high-rank and hence cannot be recovered by RPCA. We propose a novel method called robust kernel principal component analysis (RKPCA) to decompose a partially corrupted matrix as a sparse matrix plus a high or full-rank matrix with low latent dimensionality. RKPCA can be applied to many problems such as noise removal and subspace clustering and is still the only unsupervised nonlinear method robust to sparse noises. Our theoretical analysis shows that, with high probability, RKPCA can provide high recovery accuracy. The optimization of RKPCA involves nonconvex and indifferentiable problems. We propose two nonconvex optimization algorithms for RKPCA. They are alternating direction method of multipliers with backtracking line search and proximal linearized minimization with adaptive step size. Comparative studies in noise removal and robust subspace clustering corroborate the effectiveness and superiority of RKPCA. |
| Tasks | |
| Published | 2018-02-28 |
| URL | http://arxiv.org/abs/1802.10558v2 |
| http://arxiv.org/pdf/1802.10558v2.pdf | |
| PWC | https://paperswithcode.com/paper/exactly-robust-kernel-principal-component |
| Repo | |
| Framework | |
Speaker-adaptive neural vocoders for parametric speech synthesis systems
| Title | Speaker-adaptive neural vocoders for parametric speech synthesis systems |
| Authors | Eunwoo Song, Jinseob Kim, Kyungguen Byun, Hong-Goo Kang |
| Abstract | This paper proposes speaker-adaptive neural vocoders for statistical parametric speech synthesis (SPSS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive framework. However, it remains a challenge to build high-quality speech synthesis systems when the amount of a target speaker’s training data is insufficient. To generate more natural speech signals with the constraint of limited training data, we propose a speaker adaptation task with an effective variation of neural vocoding models. In the proposed method, a speaker-independent training method is applied to capture universal attributes embedded in multiple speakers, and the trained model is then optimized to represent the specific characteristics of the target speaker. Experimental results verify that the proposed SPSS systems with speaker-adaptive neural vocoders outperform those with traditional source-filter model-based vocoders and those with WaveNet vocoders, trained either speaker-dependently or speaker-independently. |
| Tasks | Speech Synthesis |
| Published | 2018-11-08 |
| URL | https://arxiv.org/abs/1811.03311v4 |
| https://arxiv.org/pdf/1811.03311v4.pdf | |
| PWC | https://paperswithcode.com/paper/speaker-adaptive-neural-vocoders-for |
| Repo | |
| Framework | |
Explanatory relations in arbitrary logics based on satisfaction systems, cutting and retraction
| Title | Explanatory relations in arbitrary logics based on satisfaction systems, cutting and retraction |
| Authors | Marc Aiguier, Jamal Atif, Isabelle Bloch, Ramón Pino-Pérez |
| Abstract | The aim of this paper is to introduce a new framework for defining abductive reasoning operators based on a notion of retraction in arbitrary logics defined as satisfaction systems. We show how this framework leads to the design of explanatory relations satisfying properties of abductive reasoning, and discuss its application to several logics. This extends previous work on propositional logics where retraction was defined as a morphological erosion. Here weaker properties are required for retraction, leading to a larger set of suitable operators for abduction for different logics. |
| Tasks | |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.01571v1 |
| http://arxiv.org/pdf/1803.01571v1.pdf | |
| PWC | https://paperswithcode.com/paper/explanatory-relations-in-arbitrary-logics |
| Repo | |
| Framework | |
On Gradient-Based Learning in Continuous Games
| Title | On Gradient-Based Learning in Continuous Games |
| Authors | Eric Mazumdar, Lillian J. Ratliff, S. Shankar Sastry |
| Abstract | We formulate a general framework for competitive gradient-based learning that encompasses a wide breadth of multi-agent learning algorithms, and analyze the limiting behavior of competitive gradient-based learning algorithms using dynamical systems theory. For both general-sum and potential games, we characterize a non-negligible subset of the local Nash equilibria that will be avoided if each agent employs a gradient-based learning algorithm. We also shed light on the issue of convergence to non-Nash strategies in general- and zero-sum games, which may have no relevance to the underlying game, and arise solely due to the choice of algorithm. The existence and frequency of such strategies may explain some of the difficulties encountered when using gradient descent in zero-sum games as, e.g., in the training of generative adversarial networks. To reinforce the theoretical contributions, we provide empirical results that highlight the frequency of linear quadratic dynamic games (a benchmark for multi-agent reinforcement learning) that admit global Nash equilibria that are almost surely avoided by policy gradient. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-04-16 |
| URL | https://arxiv.org/abs/1804.05464v3 |
| https://arxiv.org/pdf/1804.05464v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-convergence-of-gradient-based-learning |
| Repo | |
| Framework | |
Breaking the $1/\sqrt{n}$ Barrier: Faster Rates for Permutation-based Models in Polynomial Time
| Title | Breaking the $1/\sqrt{n}$ Barrier: Faster Rates for Permutation-based Models in Polynomial Time |
| Authors | Cheng Mao, Ashwin Pananjady, Martin J. Wainwright |
| Abstract | Many applications, including rank aggregation and crowd-labeling, can be modeled in terms of a bivariate isotonic matrix with unknown permutations acting on its rows and columns. We consider the problem of estimating such a matrix based on noisy observations of a subset of its entries, and design and analyze a polynomial-time algorithm that improves upon the state of the art. In particular, our results imply that any such $n \times n$ matrix can be estimated efficiently in the normalized Frobenius norm at rate $\widetilde{\mathcal O}(n^{-3/4})$, thus narrowing the gap between $\widetilde{\mathcal O}(n^{-1})$ and $\widetilde{\mathcal O}(n^{-1/2})$, which were hitherto the rates of the most statistically and computationally efficient methods, respectively. |
| Tasks | |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09963v3 |
| http://arxiv.org/pdf/1802.09963v3.pdf | |
| PWC | https://paperswithcode.com/paper/breaking-the-1sqrtn-barrier-faster-rates-for |
| Repo | |
| Framework | |
Using Linguistic Cues for Analyzing Social Movements
| Title | Using Linguistic Cues for Analyzing Social Movements |
| Authors | Rezvaneh Rezapour |
| Abstract | With the growth of social media usage, social activists try to leverage this platform to raise the awareness related to a social issue and engage the public worldwide. The broad use of social media platforms in recent years, made it easier for the people to stay up-to-date on the news related to regional and worldwide events. While social media, namely Twitter, assists social movements to connect with more people and mobilize the movement, traditional media such as news articles help in spreading the news related to the events in a broader aspect. In this study, we analyze linguistic features and cues, such as individualism vs. pluralism, sentiment and emotion to examine the relationship between the medium and discourse over time. We conduct this work in a specific application context, the “Black Lives Matter” (BLM) movement, and compare discussions related to this event in social media vs. news articles. |
| Tasks | |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.01742v1 |
| http://arxiv.org/pdf/1808.01742v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-linguistic-cues-for-analyzing-social |
| Repo | |
| Framework | |
Character-level Chinese-English Translation through ASCII Encoding
| Title | Character-level Chinese-English Translation through ASCII Encoding |
| Authors | Nikola I. Nikolov, Yuhuang Hu, Mi Xue Tan, Richard H. R. Hahnloser |
| Abstract | Character-level Neural Machine Translation (NMT) models have recently achieved impressive results on many language pairs. They mainly do well for Indo-European language pairs, where the languages share the same writing system. However, for translating between Chinese and English, the gap between the two different writing systems poses a major challenge because of a lack of systematic correspondence between the individual linguistic units. In this paper, we enable character-level NMT for Chinese, by breaking down Chinese characters into linguistic units similar to that of Indo-European languages. We use the Wubi encoding scheme, which preserves the original shape and semantic information of the characters, while also being reversible. We show promising results from training Wubi-based models on the character- and subword-level with recurrent as well as convolutional models. |
| Tasks | Machine Translation |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03330v2 |
| http://arxiv.org/pdf/1805.03330v2.pdf | |
| PWC | https://paperswithcode.com/paper/character-level-chinese-english-translation |
| Repo | |
| Framework | |
Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
| Title | Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size |
| Authors | J. Bialopetravičius, D. Narbutis, V. Vansevičius |
| Abstract | Context. Convolutional neural networks (CNNs) have been proven to perform fast classification and detection on natural images and have potential to infer astrophysical parameters on the exponentially increasing amount of sky survey imaging data. The inference pipeline can be trained either from real human-annotated data or simulated mock observations. Until now star cluster analysis was based on integral or individual resolved stellar photometry. This limits the amount of information that can be extracted from cluster images. Aims. Develop a CNN-based algorithm aimed to simultaneously derive ages, masses, and sizes of star clusters directly from multi-band images. Demonstrate CNN capabilities on low mass semi-resolved star clusters in a low signal-to-noise ratio regime. Methods. A CNN was constructed based on the deep residual network (ResNet) architecture and trained on simulated images of star clusters with various ages, masses, and sizes. To provide realistic backgrounds, M31 star fields taken from the PHAT survey were added to the mock cluster images. Results. The proposed CNN was verified on mock images of artificial clusters and has demonstrated high precision and no significant bias for clusters of ages $\lesssim$3Gyr and masses between 250 and 4,000 ${\rm M_\odot}$. The pipeline is end-to-end, starting from input images all the way to the inferred parameters; no hand-coded steps have to be performed: estimates of parameters are provided by the neural network in one inferential step from raw images. |
| Tasks | |
| Published | 2018-07-19 |
| URL | http://arxiv.org/abs/1807.07658v2 |
| http://arxiv.org/pdf/1807.07658v2.pdf | |
| PWC | https://paperswithcode.com/paper/deriving-star-cluster-parameters-with |
| Repo | |
| Framework | |
Multisource and Multitemporal Data Fusion in Remote Sensing
| Title | Multisource and Multitemporal Data Fusion in Remote Sensing |
| Authors | Pedram Ghamisi, Behnood Rasti, Naoto Yokoya, Qunming Wang, Bernhard Hofle, Lorenzo Bruzzone, Francesca Bovolo, Mingmin Chi, Katharina Anders, Richard Gloaguen, Peter M. Atkinson, Jon Atli Benediktsson |
| Abstract | The sharp and recent increase in the availability of data captured by different sensors combined with their considerably heterogeneous natures poses a serious challenge for the effective and efficient processing of remotely sensed data. Such an increase in remote sensing and ancillary datasets, however, opens up the possibility of utilizing multimodal datasets in a joint manner to further improve the performance of the processing approaches with respect to the application at hand. Multisource data fusion has, therefore, received enormous attention from researchers worldwide for a wide variety of applications. Moreover, thanks to the revisit capability of several spaceborne sensors, the integration of the temporal information with the spatial and/or spectral/backscattering information of the remotely sensed data is possible and helps to move from a representation of 2D/3D data to 4D data structures, where the time variable adds new information as well as challenges for the information extraction algorithms. There are a huge number of research works dedicated to multisource and multitemporal data fusion, but the methods for the fusion of different modalities have expanded in different paths according to each research community. This paper brings together the advances of multisource and multitemporal data fusion approaches with respect to different research communities and provides a thorough and discipline-specific starting point for researchers at different levels (i.e., students, researchers, and senior researchers) willing to conduct novel investigations on this challenging topic by supplying sufficient detail and references. |
| Tasks | |
| Published | 2018-12-19 |
| URL | http://arxiv.org/abs/1812.08287v1 |
| http://arxiv.org/pdf/1812.08287v1.pdf | |
| PWC | https://paperswithcode.com/paper/multisource-and-multitemporal-data-fusion-in |
| Repo | |
| Framework | |
