Paper Group ANR 951
Efficient surrogate modeling methods for large-scale Earth system models based on machine learning techniques. Generating Justifications for Norm-Related Agent Decisions. Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters. Deep Multi-Agent Reinforcement Learning Based Cooperative Edge Caching in Wireless N …
Efficient surrogate modeling methods for large-scale Earth system models based on machine learning techniques
| Title | Efficient surrogate modeling methods for large-scale Earth system models based on machine learning techniques |
| Authors | Dan Lu, Daniel Ricciuto |
| Abstract | Improving predictive understanding of Earth system variability and change requires data-model integration. Efficient data-model integration for complex models requires surrogate modeling to reduce model evaluation time. However, building a surrogate of a large-scale Earth system model (ESM) with many output variables is computationally intensive because it involves a large number of expensive ESM simulations. In this effort, we propose an efficient surrogate method capable of using a few ESM runs to build an accurate and fast-to-evaluate surrogate system of model outputs over large spatial and temporal domains. We first use singular value decomposition to reduce the output dimensions, and then use Bayesian optimization techniques to generate an accurate neural network surrogate model based on limited ESM simulation samples. Our machine learning based surrogate methods can build and evaluate a large surrogate system of many variables quickly. Thus, whenever the quantities of interest change such as a different objective function, a new site, and a longer simulation time, we can simply extract the information of interest from the surrogate system without rebuilding new surrogates, which significantly saves computational efforts. We apply the proposed method to a regional ecosystem model to approximate the relationship between 8 model parameters and 42660 carbon flux outputs. Results indicate that using only 20 model simulations, we can build an accurate surrogate system of the 42660 variables, where the consistency between the surrogate prediction and actual model simulation is 0.93 and the mean squared error is 0.02. This highly-accurate and fast-to-evaluate surrogate system will greatly enhance the computational efficiency in data-model integration to improve predictions and advance our understanding of the Earth system. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.05125v1 |
| http://arxiv.org/pdf/1901.05125v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-surrogate-modeling-methods-for |
| Repo | |
| Framework | |
Generating Justifications for Norm-Related Agent Decisions
| Title | Generating Justifications for Norm-Related Agent Decisions |
| Authors | Daniel Kasenberg, Antonio Roque, Ravenna Thielstrom, Meia Chita-Tegmark, Matthias Scheutz |
| Abstract | We present an approach to generating natural language justifications of decisions derived from norm-based reasoning. Assuming an agent which maximally satisfies a set of rules specified in an object-oriented temporal logic, the user can ask factual questions (about the agent’s rules, actions, and the extent to which the agent violated the rules) as well as “why” questions that require the agent comparing actual behavior to counterfactual trajectories with respect to these rules. To produce natural-sounding explanations, we focus on the subproblem of producing natural language clauses from statements in a fragment of temporal logic, and then describe how to embed these clauses into explanatory sentences. We use a human judgment evaluation on a testbed task to compare our approach to variants in terms of intelligibility, mental model and perceived trust. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00226v1 |
| https://arxiv.org/pdf/1911.00226v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-justifications-for-norm-related |
| Repo | |
| Framework | |
Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters
| Title | Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters |
| Authors | Niccoló Nicodemo, Gaurav Naithani, Konstantinos Drossos, Tuomas Virtanen, Roberto Saletti |
| Abstract | Effective employment of deep neural networks (DNNs) in mobile devices and embedded systems is hampered by requirements for memory and computational power. This paper presents a non-uniform quantization approach which allows for dynamic quantization of DNN parameters for different layers and within the same layer. A virtual bit shift (VBS) scheme is also proposed to improve the accuracy of the proposed scheme. Our method reduces the memory requirements, preserving the performance of the network. The performance of our method is validated in a speech enhancement application, where a fully connected DNN is used to predict the clean speech spectrum from the input noisy speech spectrum. A DNN is optimized and its memory footprint and performance are evaluated using the short-time objective intelligibility, STOI, metric. The application of the low-bit quantization allows a 50% reduction of the DNN memory footprint while the STOI performance drops only by 2.7%. |
| Tasks | Quantization, Speech Enhancement |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.00527v1 |
| https://arxiv.org/pdf/1911.00527v1.pdf | |
| PWC | https://paperswithcode.com/paper/memory-requirement-reduction-of-deep-neural |
| Repo | |
| Framework | |
Deep Multi-Agent Reinforcement Learning Based Cooperative Edge Caching in Wireless Networks
| Title | Deep Multi-Agent Reinforcement Learning Based Cooperative Edge Caching in Wireless Networks |
| Authors | Chen Zhong, M. Cenk Gursoy, Senem Velipasalar |
| Abstract | The growing demand on high-quality and low-latency multimedia services has led to much interest in edge caching techniques. Motivated by this, we in this paper consider edge caching at the base stations with unknown content popularity distributions. To solve the dynamic control problem of making caching decisions, we propose a deep actor-critic reinforcement learning based multi-agent framework with the aim to minimize the overall average transmission delay. To evaluate the proposed framework, we compare the learning-based performance with three other caching policies, namely least recently used (LRU), least frequently used (LFU), and first-in-first-out (FIFO) policies. Through simulation results, performance improvements of the proposed framework over these three caching algorithms have been identified and its superior ability to adapt to varying environments is demonstrated. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.05256v1 |
| https://arxiv.org/pdf/1905.05256v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multi-agent-reinforcement-learning-based |
| Repo | |
| Framework | |
Recommendation or Discrimination?: Quantifying Distribution Parity in Information Retrieval Systems
| Title | Recommendation or Discrimination?: Quantifying Distribution Parity in Information Retrieval Systems |
| Authors | Rinat Khaziev, Bryce Casavant, Pearce Washabaugh, Amy A. Winecoff, Matthew Graham |
| Abstract | Information retrieval (IR) systems often leverage query data to suggest relevant items to users. This introduces the possibility of unfairness if the query (i.e., input) and the resulting recommendations unintentionally correlate with latent factors that are protected variables (e.g., race, gender, and age). For instance, a visual search system for fashion recommendations may pick up on features of the human models rather than fashion garments when generating recommendations. In this work, we introduce a statistical test for “distribution parity” in the top-K IR results, which assesses whether a given set of recommendations is fair with respect to a specific protected variable. We evaluate our test using both simulated and empirical results. First, using artificially biased recommendations, we demonstrate the trade-off between statistically detectable bias and the size of the search catalog. Second, we apply our test to a visual search system for fashion garments, specifically testing for recommendation bias based on the skin tone of fashion models. Our distribution parity test can help ensure that IR systems’ results are fair and produce a good experience for all users. |
| Tasks | Information Retrieval |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06429v1 |
| https://arxiv.org/pdf/1909.06429v1.pdf | |
| PWC | https://paperswithcode.com/paper/recommendation-or-discrimination-quantifying |
| Repo | |
| Framework | |
The Wilderness Area Data Set: Adapting the Covertype data set for unsupervised learning
| Title | The Wilderness Area Data Set: Adapting the Covertype data set for unsupervised learning |
| Authors | Richard Hugh Moulton, Jakub Zgraja |
| Abstract | Benchmark data sets are of vital importance in machine learning research, as indicated by the number of repositories that exist to make them publicly available. Although many of these are usable in the stream mining context as well, it is less obvious which data sets can be used to evaluate data stream clustering algorithms. We note that the classic Covertype data set’s size makes it attractive for use in stream mining but unfortunately it is specifically designed for classification. Here we detail the process of transforming the Covertype data set into one amenable for unsupervised learning, which we call the Wilderness Area data set. Our quantitative analysis allows us to conclude that the Wilderness Area data set is more appropriate for unsupervised learning than the original Covertype data set. |
| Tasks | |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.11040v1 |
| http://arxiv.org/pdf/1901.11040v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-wilderness-area-data-set-adapting-the |
| Repo | |
| Framework | |
Comparative Study between Adversarial Networks and Classical Techniques for Speech Enhancement
| Title | Comparative Study between Adversarial Networks and Classical Techniques for Speech Enhancement |
| Authors | Tito Spadini, Ricardo Suyama |
| Abstract | Speech enhancement is a crucial task for several applications. Among the most explored techniques are the Wiener filter and the LogMMSE, but approaches exploring deep learning adapted to this task, such as SEGAN, have presented relevant results. This study compared the performance of the mentioned techniques in 85 noise conditions regarding quality, intelligibility, and distortion; and concluded that classical techniques continue to exhibit superior results for most scenarios, but, in severe noise scenarios, SEGAN performed better and with lower variance. |
| Tasks | Speech Enhancement |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09522v1 |
| https://arxiv.org/pdf/1910.09522v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparative-study-between-adversarial |
| Repo | |
| Framework | |
AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks
| Title | AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks |
| Authors | Sherif Abdulatif, Karim Armanious, Karim Guirguis, Jayasankar T. Sajeev, Bin Yang |
| Abstract | Automatic speech recognition (ASR) systems are of vital importance nowadays in commonplace tasks such as speech-to-text processing and language translation. This created the need for an ASR system that can operate in realistic crowded environments. Thus, speech enhancement is a fundamental building block in ASR systems and other applications such as hearing aids, smartphones and teleconferencing systems. In this paper, a generative adversarial network (GAN) based framework is investigated for the task of speech enhancement, more specifically speech denoising of audio tracks. A new architecture based on CasNet generator and an additional perceptual loss are incorporated to get realistically denoised speech phonetics. Finally, the proposed framework is shown to outperform other learning and traditional model-based speech enhancement approaches. |
| Tasks | Denoising, Speech Enhancement, Speech Recognition |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.12620v2 |
| https://arxiv.org/pdf/1910.12620v2.pdf | |
| PWC | https://paperswithcode.com/paper/perceptual-speech-enhancement-via-generative |
| Repo | |
| Framework | |
Calibrated model-based evidential clustering using bootstrapping
| Title | Calibrated model-based evidential clustering using bootstrapping |
| Authors | Thierry Denoeux |
| Abstract | Evidential clustering is an approach to clustering in which cluster-membership uncertainty is represented by a collection of Dempster-Shafer mass functions forming an evidential partition. In this paper, we propose to construct these mass functions by bootstrapping finite mixture models. In the first step, we compute bootstrap percentile confidence intervals for all pairwise probabilities (the probabilities for any two objects to belong to the same class). We then construct an evidential partition such that the pairwise belief and plausibility degrees approximate the bounds of the confidence intervals. This evidential partition is calibrated, in the sense that the pairwise belief-plausibility intervals contain the true probabilities “most of the time”, i.e., with a probability close to the defined confidence level. This frequentist property is verified by simulation, and the practical applicability of the method is demonstrated using several real datasets. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06137v1 |
| https://arxiv.org/pdf/1912.06137v1.pdf | |
| PWC | https://paperswithcode.com/paper/calibrated-model-based-evidential-clustering |
| Repo | |
| Framework | |
Seeing Voices in Noise: A Study of Audiovisual-Enhanced Vocoded Speech Intelligibility in Cochlear Implant Simulation
| Title | Seeing Voices in Noise: A Study of Audiovisual-Enhanced Vocoded Speech Intelligibility in Cochlear Implant Simulation |
| Authors | Rung-Yu Tseng, Tao-Wei Wang, Szu-Wei Fu, Yu Tsao, Chia-Ying Lee |
| Abstract | Speech perception is a key to verbal communication. For people with hearing loss, the capability to recognize speech is restricted, particularly in the noisy environment. This study aimed to understand the improvement for vocoded speech intelligibility in cochlear implant (CI) simulation through two potential methods: Speech Enhancement (SE) and Audiovisual Integration. A fully convolutional neural network (FCN) using an intelligibility-oriented objective function was recently proposed and proven to effectively facilitate the speech intelligibility as an advanced SE approach. Furthermore, the audiovisual integration is reported to supply better speech comprehension compared to audio-only information. An experiment was designed to test speech intelligibility using tone-vocoded speech in CI simulation with a group of normal-hearing listeners. Experimental results confirmed the effectiveness of the FCN-based SE and audiovisual integration and positively recommended these two methods becoming a blended feature in a CI processor to increase the speech intelligibility for CI users under noisy conditions. |
| Tasks | Speech Enhancement |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.11919v1 |
| https://arxiv.org/pdf/1909.11919v1.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-voices-in-noise-a-study-of-audiovisual |
| Repo | |
| Framework | |
Report on the 8th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2019)
| Title | Report on the 8th International Workshop on Bibliometric-enhanced Information Retrieval (BIR 2019) |
| Authors | Guillaume Cabanac, Ingo Frommholz, Philipp Mayr |
| Abstract | The Bibliometric-enhanced Information Retrieval workshop series (BIR) at ECIR tackled issues related to academic search, at the crossroads between Information Retrieval and Bibliometrics. BIR is a hot topic investigated by both academia (e.g., ArnetMiner, CiteSeerx, DocEar) and the industry (e.g., Google Scholar, Microsoft Academic Search, Semantic Scholar). This report presents the 8th iteration of the one-day BIR workshop held at ECIR 2019 in Cologne, Germany. |
| Tasks | Information Retrieval |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.04954v1 |
| https://arxiv.org/pdf/1909.04954v1.pdf | |
| PWC | https://paperswithcode.com/paper/report-on-the-8th-international-workshop-on |
| Repo | |
| Framework | |
Learning Conceptual-Contextual Embeddings for Medical Text
| Title | Learning Conceptual-Contextual Embeddings for Medical Text |
| Authors | Xiao Zhang, Dejing Dou, Ji Wu |
| Abstract | External knowledge is often useful for natural language understanding tasks. We introduce a contextual text representation model called Conceptual-Contextual (CC) embeddings, which incorporates structured knowledge into text representations. Unlike entity embedding methods, our approach encodes a knowledge graph into a context model. CC embeddings can be easily reused for a wide range of tasks just like pre-trained language models. Our model effectively encodes the huge UMLS database by leveraging semantic generalizability. Experiments on electronic health records (EHRs) and medical text processing benchmarks showed our model gives a major boost to the performance of supervised medical NLP tasks. |
| Tasks | |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06203v3 |
| https://arxiv.org/pdf/1908.06203v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-conceptual-contexual-embeddings-for |
| Repo | |
| Framework | |
Exponential Family Estimation via Adversarial Dynamics Embedding
| Title | Exponential Family Estimation via Adversarial Dynamics Embedding |
| Authors | Bo Dai, Zhen Liu, Hanjun Dai, Niao He, Arthur Gretton, Le Song, Dale Schuurmans |
| Abstract | We present an efficient algorithm for maximum likelihood estimation (MLE) of exponential family models, with a general parametrization of the energy function that includes neural networks. We exploit the primal-dual view of the MLE with a kinetics augmented model to obtain an estimate associated with an adversarial dual sampler. To represent this sampler, we introduce a novel neural architecture, dynamics embedding, that generalizes Hamiltonian Monte-Carlo (HMC). The proposed approach inherits the flexibility of HMC while enabling tractable entropy estimation for the augmented model. By learning both a dual sampler and the primal model simultaneously, and sharing parameters between them, we obviate the requirement to design a separate sampling procedure once the model has been trained, leading to more effective learning. We show that many existing estimators, such as contrastive divergence, pseudo/composite-likelihood, score matching, minimum Stein discrepancy estimator, non-local contrastive objectives, noise-contrastive estimation, and minimum probability flow, are special cases of the proposed approach, each expressed by a different (fixed) dual sampler. An empirical investigation shows that adapting the sampler during MLE can significantly improve on state-of-the-art estimators. |
| Tasks | |
| Published | 2019-04-27 |
| URL | https://arxiv.org/abs/1904.12083v3 |
| https://arxiv.org/pdf/1904.12083v3.pdf | |
| PWC | https://paperswithcode.com/paper/exponential-family-estimation-via-adversarial |
| Repo | |
| Framework | |
Blind Deconvolution Method using Omnidirectional Gabor Filter-based Edge Information
| Title | Blind Deconvolution Method using Omnidirectional Gabor Filter-based Edge Information |
| Authors | Trung Dung Do, Xuenan Cui, Thi Hai Binh Nguyen, Hakil Kim, Van Huan Nguyen |
| Abstract | In the previous blind deconvolution methods, de-blurred images can be obtained by using the edge or pixel information. However, the existing edge-based methods did not take advantage of edge information in ommi-directions, but only used horizontal and vertical edges when recovering the de-blurred images. This limitation lowers the quality of the recovered images. This paper proposes a method which utilizes edges in different directions to recover the true sharp image. We also provide a statistical table score to show how many directions are enough to recover a high quality true sharp image. In order to grade the quality of the deblurring image, we introduce a measurement, namely Haar defocus score that takes advantage of the Haar-Wavelet transform. The experimental results prove that the proposed method obtains a high quality deblurred image with respect to both the Haar defocus score and the Peak Signal to Noise Ratio. |
| Tasks | Deblurring |
| Published | 2019-05-03 |
| URL | https://arxiv.org/abs/1905.01003v1 |
| https://arxiv.org/pdf/1905.01003v1.pdf | |
| PWC | https://paperswithcode.com/paper/blind-deconvolution-method-using |
| Repo | |
| Framework | |
Improving the Intelligibility of Electric and Acoustic Stimulation Speech Using Fully Convolutional Networks Based Speech Enhancement
| Title | Improving the Intelligibility of Electric and Acoustic Stimulation Speech Using Fully Convolutional Networks Based Speech Enhancement |
| Authors | Natalie Yu-Hsien Wang, Hsiao-Lan Sharon Wang, Tao-Wei Wang, Szu-Wei Fu, Xugan Lu, Yu Tsao, Hsin-Min Wang |
| Abstract | The combined electric and acoustic stimulation (EAS) has demonstrated better speech recognition than conventional cochlear implant (CI) and yielded satisfactory performance under quiet conditions. However, when noise signals are involved, both the electric signal and the acoustic signal may be distorted, thereby resulting in poor recognition performance. To suppress noise effects, speech enhancement (SE) is a necessary unit in EAS devices. Recently, a time-domain speech enhancement algorithm based on the fully convolutional neural networks (FCN) with a short-time objective intelligibility (STOI)-based objective function (termed FCN(S) in short) has received increasing attention due to its simple structure and effectiveness of restoring clean speech signals from noisy counterparts. With evidence showing the benefits of FCN(S) for normal speech, this study sets out to assess its ability to improve the intelligibility of EAS simulated speech. Objective evaluations and listening tests were conducted to examine the performance of FCN(S) in improving the speech intelligibility of normal and vocoded speech in noisy environments. The experimental results show that, compared with the traditional minimum-mean square-error SE method and the deep denoising autoencoder SE method, FCN(S) can obtain better gain in the speech intelligibility for normal as well as vocoded speech. This study, being the first to evaluate deep learning SE approaches for EAS, confirms that FCN(S) is an effective SE approach that may potentially be integrated into an EAS processor to benefit users in noisy environments. |
| Tasks | Denoising, Speech Enhancement, Speech Recognition |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.11912v1 |
| https://arxiv.org/pdf/1909.11912v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-the-intelligibility-of-electric-and |
| Repo | |
| Framework | |
