Paper Group ANR 1245
HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning. Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms. Syntax-Infused Variational Autoencoder for Text Generation. Attention-Privileged Reinforcement Learning. Marker based Thermal-Inertial Localization for Aerial Robots in Obscurant Filled E …
HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning
| Title | HybridAlpha: An Efficient Approach for Privacy-Preserving Federated Learning |
| Authors | Runhua Xu, Nathalie Baracaldo, Yi Zhou, Ali Anwar, Heiko Ludwig |
| Abstract | Federated learning has emerged as a promising approach for collaborative and privacy-preserving learning. Participants in a federated learning process cooperatively train a model by exchanging model parameters instead of the actual training data, which they might want to keep private. However, parameter interaction and the resulting model still might disclose information about the training data used. To address these privacy concerns, several approaches have been proposed based on differential privacy and secure multiparty computation (SMC), among others. They often result in large communication overhead and slow training time. In this paper, we propose HybridAlpha, an approach for privacy-preserving federated learning employing an SMC protocol based on functional encryption. This protocol is simple, efficient and resilient to participants dropping out. We evaluate our approach regarding the training time and data volume exchanged using a federated learning process to train a CNN on the MNIST data set. Evaluation against existing crypto-based SMC solutions shows that HybridAlpha can reduce the training time by 68% and data transfer volume by 92% on average while providing the same model performance and privacy guarantees as the existing solutions. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.05897v1 |
| https://arxiv.org/pdf/1912.05897v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybridalpha-an-efficient-approach-for-privacy |
| Repo | |
| Framework | |
Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
| Title | Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms |
| Authors | Kaiqing Zhang, Zhuoran Yang, Tamer Başar |
| Abstract | Recent years have witnessed significant advances in reinforcement learning (RL), which has registered great success in solving various sequential decision-making problems in machine learning. Most of the successful RL applications, e.g., the games of Go and Poker, robotics, and autonomous driving, involve the participation of more than one single agent, which naturally fall into the realm of multi-agent RL (MARL), a domain with a relatively long history, and has recently re-emerged due to advances in single-agent RL techniques. Though empirically successful, theoretical foundations for MARL are relatively lacking in the literature. In this chapter, we provide a selective overview of MARL, with focus on algorithms backed by theoretical analysis. More specifically, we review the theoretical results of MARL algorithms mainly within two representative frameworks, Markov/stochastic games and extensive-form games, in accordance with the types of tasks they address, i.e., fully cooperative, fully competitive, and a mix of the two. We also introduce several significant but challenging applications of these algorithms. Orthogonal to the existing reviews on MARL, we highlight several new angles and taxonomies of MARL theory, including learning in extensive-form games, decentralized MARL with networked agents, MARL in the mean-field regime, (non-)convergence of policy-based methods for learning in games, etc. Some of the new angles extrapolate from our own research endeavors and interests. Our overall goal with this chapter is, beyond providing an assessment of the current state of the field on the mark, to identify fruitful future research directions on theoretical studies of MARL. We expect this chapter to serve as continuing stimulus for researchers interested in working on this exciting while challenging topic. |
| Tasks | Autonomous Driving, Decision Making, Multi-agent Reinforcement Learning |
| Published | 2019-11-24 |
| URL | https://arxiv.org/abs/1911.10635v1 |
| https://arxiv.org/pdf/1911.10635v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-agent-reinforcement-learning-a |
| Repo | |
| Framework | |
Syntax-Infused Variational Autoencoder for Text Generation
| Title | Syntax-Infused Variational Autoencoder for Text Generation |
| Authors | Xinyuan Zhang, Yi Yang, Siyang Yuan, Dinghan Shen, Lawrence Carin |
| Abstract | We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences. Distinct from existing VAE-based text generative models, SIVAE contains two separate latent spaces, for sentences and syntactic trees. The evidence lower bound objective is redesigned correspondingly, by optimizing a joint distribution that accommodates two encoders and two decoders. SIVAE works with long short-term memory architectures to simultaneously generate sentences and syntactic trees. Two versions of SIVAE are proposed: one captures the dependencies between the latent variables through a conditional prior network, and the other treats the latent variables independently such that syntactically-controlled sentence generation can be performed. Experimental results demonstrate the generative superiority of SIVAE on both reconstruction and targeted syntactic evaluations. Finally, we show that the proposed models can be used for unsupervised paraphrasing given different syntactic tree templates. |
| Tasks | Text Generation |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02181v1 |
| https://arxiv.org/pdf/1906.02181v1.pdf | |
| PWC | https://paperswithcode.com/paper/syntax-infused-variational-autoencoder-for |
| Repo | |
| Framework | |
Attention-Privileged Reinforcement Learning
| Title | Attention-Privileged Reinforcement Learning |
| Authors | Sasha Salter, Dushyant Rao, Markus Wulfmeier, Raia Hadsell, Ingmar Posner |
| Abstract | Reinforcement learning is known to suffer from poor sample efficiency and generalisation to unseen environments. Domain randomisation encourages transfer by training over factors of variation that may be encountered in the target domain. This increases learning complexity, can negatively impact learning rate and performance, and requires knowledge of potential variations during deployment. In this paper, we introduce Attention-Privileged Reinforcement Learning (APRiL) which uses a self-supervised attention mechanism to significantly alleviate these drawbacks: by focusing on task-relevant aspects of the observations, attention provides robustness to distractors as well as significantly increased learning efficiency. APRiL trains two attention-augmented actor-critic agents: one purely based on image observations, available across training and transfer domains; and one with access to privileged information (such as environment states) available only during training. Experience is shared between both agents and their attention mechanisms are aligned. The image-based policy can then be deployed without access to privileged information. We experimentally demonstrate accelerated and more robust learning on a diverse set of domains, leading to improved final performance for environments both within and outside the training distribution. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08363v2 |
| https://arxiv.org/pdf/1911.08363v2.pdf | |
| PWC | https://paperswithcode.com/paper/attention-privileged-reinforcement-learning-1 |
| Repo | |
| Framework | |
Marker based Thermal-Inertial Localization for Aerial Robots in Obscurant Filled Environments
| Title | Marker based Thermal-Inertial Localization for Aerial Robots in Obscurant Filled Environments |
| Authors | Shehryar Khattak, Christos Papachristos, Kostas Alexis |
| Abstract | For robotic inspection tasks in known environments fiducial markers provide a reliable and low-cost solution for robot localization. However, detection of such markers relies on the quality of RGB camera data, which degrades significantly in the presence of visual obscurants such as fog and smoke. The ability to navigate known environments in the presence of obscurants can be critical for inspection tasks especially, in the aftermath of a disaster. Addressing such a scenario, this work proposes a method for the design of fiducial markers to be used with thermal cameras for the pose estimation of aerial robots. Our low cost markers are designed to work in the long wave infrared spectrum, which is not affected by the presence of obscurants, and can be affixed to any object that has measurable temperature difference with respect to its surroundings. Furthermore, the estimated pose from the fiducial markers is fused with inertial measurements in an extended Kalman filter to remove high frequency noise and error present in the fiducial pose estimates. The proposed markers and the pose estimation method are experimentally evaluated in an obscurant filled environment using an aerial robot carrying a thermal camera. |
| Tasks | Pose Estimation |
| Published | 2019-03-02 |
| URL | http://arxiv.org/abs/1903.00782v1 |
| http://arxiv.org/pdf/1903.00782v1.pdf | |
| PWC | https://paperswithcode.com/paper/marker-based-thermal-inertial-localization |
| Repo | |
| Framework | |
Reverse Experience Replay
| Title | Reverse Experience Replay |
| Authors | Egor Rotinov |
| Abstract | This paper describes an improvement in Deep Q-learning called Reverse Experience Replay (also RER) that solves the problem of sparse rewards and helps to deal with reward maximizing tasks by sampling transitions successively in reverse order. On tasks with enough experience for training and enough Experience Replay memory capacity, Deep Q-learning Network with Reverse Experience Replay shows competitive results against both Double DQN, with a standard Experience Replay, and vanilla DQN. Also, RER achieves significantly increased results in tasks with a lack of experience and Replay memory capacity. |
| Tasks | Q-Learning |
| Published | 2019-10-19 |
| URL | https://arxiv.org/abs/1910.08780v2 |
| https://arxiv.org/pdf/1910.08780v2.pdf | |
| PWC | https://paperswithcode.com/paper/reverse-experience-replay |
| Repo | |
| Framework | |
DCNN-GAN: Reconstructing Realistic Image from fMRI
| Title | DCNN-GAN: Reconstructing Realistic Image from fMRI |
| Authors | Yunfeng Lin, Jiangbei Li, Hanjing Wang |
| Abstract | Visualizing the perceptual content by analyzing human functional magnetic resonance imaging (fMRI) has been an active research area. However, due to its high dimensionality, complex dimensional structure, and small number of samples available, reconstructing realistic images from fMRI remains challenging. Recently with the development of convolutional neural network (CNN) and generative adversarial network (GAN), mapping multi-voxel fMRI data to complex, realistic images has been made possible. In this paper, we propose a model, DCNN-GAN, by combining a reconstruction network and GAN. We utilize the CNN for hierarchical feature extraction and the DCNN-GAN to reconstruct more realistic images. Extensive experiments have been conducted, showing that our method outperforms previous works, regarding reconstruction quality and computational cost. |
| Tasks | |
| Published | 2019-01-13 |
| URL | http://arxiv.org/abs/1901.07368v1 |
| http://arxiv.org/pdf/1901.07368v1.pdf | |
| PWC | https://paperswithcode.com/paper/dcnn-gan-reconstructing-realistic-image-from |
| Repo | |
| Framework | |
Improved Dynamic Time Warping (DTW) Approach for Online Signature Verification
| Title | Improved Dynamic Time Warping (DTW) Approach for Online Signature Verification |
| Authors | Azhar Ahmad Jaini, Ghazali Sulong, Amjad Rehman |
| Abstract | Online signature verification is the process of verifying time series signature data which is generally obtained from the tablet-based device. Unlike offline signature images, the online signature image data consists of points that are arranged in a sequence of time. The aim of this research is to develop an improved approach to map the strokes in both test and reference signatures. Current methods make use of the Dynamic Time Warping (DTW) algorithm and its variant to segment them before comparing each of its data dimension. This paper presents a modified DTW algorithm with the proposed Lost Box Recovery Algorithm aims to improve the mapping performance for online signature verification |
| Tasks | Time Series |
| Published | 2019-03-26 |
| URL | http://arxiv.org/abs/1904.00786v1 |
| http://arxiv.org/pdf/1904.00786v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-dynamic-time-warping-dtw-approach |
| Repo | |
| Framework | |
Neural Dynamics on Complex Networks
| Title | Neural Dynamics on Complex Networks |
| Authors | Chengxi Zang, Fei Wang |
| Abstract | We introduce a deep learning model to learn continuous-time dynamics on complex networks and infer the semantic labels of nodes in the network at terminal time. We formulate the problem as an optimal control problem by minimizing a loss function consisting of a running loss of network dynamics, a terminal loss of nodes’ labels, and a neural-differential-equation-system constraint. We solve the problem by a differential deep learning framework: as for the forward process of the system, rather than forwarding through a discrete number of hidden layers, we integrate the ordinary differential equation systems on graphs over continuous time; as for the backward learning process, we learn the optimal control parameters by back-propagation during solving initial value problem. We validate our model by learning complex dynamics on various real-world complex networks, and then apply our model to graph semi-supervised classification tasks. The promising experimental results demonstrate our model’s capability of jointly capturing the structure, dynamics and semantics of complex systems. |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06491v1 |
| https://arxiv.org/pdf/1908.06491v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-dynamics-on-complex-networks |
| Repo | |
| Framework | |
Predicting Features of Quantum Systems from Very Few Measurements
| Title | Predicting Features of Quantum Systems from Very Few Measurements |
| Authors | Hsin-Yuan Huang, Richard Kueng |
| Abstract | Predicting features of complex, large-scale quantum systems is essential to the characterization and engineering of quantum architectures. We present an efficient approach for constructing an approximate classical description, called the classical shadow, of a quantum system from very few quantum measurements that can later be used to predict a large collection of features. This approach is guaranteed to accurately predict M linear functions with bounded Hilbert-Schmidt norm from only order of log(M) measurements. This is completely independent of the system size and saturates fundamental lower bounds from information theory. We support our theoretical findings with numerical experiments over a wide range of problem sizes (2 to 162 qubits). These highlight advantages compared to existing machine learning approaches. |
| Tasks | |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08909v2 |
| https://arxiv.org/pdf/1908.08909v2.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-features-of-quantum-systems-using |
| Repo | |
| Framework | |
Semantic Mask for Transformer based End-to-End Speech Recognition
| Title | Semantic Mask for Transformer based End-to-End Speech Recognition |
| Authors | Chengyi Wang, Yu Wu, Yujiao Du, Jinyu Li, Shujie Liu, Liang Lu, Shuo Ren, Guoli Ye, Sheng Zhao, Ming Zhou |
| Abstract | Attention-based encoder-decoder model has achieved impressive results for both automatic speech recognition (ASR) and text-to-speech (TTS) tasks. This approach takes advantage of the memorization capacity of neural networks to learn the mapping from the input sequence to the output sequence from scratch, without the assumption of prior knowledge such as the alignments. However, this model is prone to overfitting, especially when the amount of training data is limited. Inspired by SpecAugment and BERT, in this paper, we propose a semantic mask based regularization for training such kind of end-to-end (E2E) model. The idea is to mask the input features corresponding to a particular output token, e.g., a word or a word-piece, in order to encourage the model to fill the token based on the contextual information. While this approach is applicable to the encoder-decoder framework with any type of neural network architecture, we study the transformer-based model for ASR in this work. We perform experiments on Librispeech 960h and TedLium2 data sets, and achieve the state-of-the-art performance on the test set in the scope of E2E models. |
| Tasks | End-To-End Speech Recognition, Speech Recognition |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03010v2 |
| https://arxiv.org/pdf/1912.03010v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-mask-for-transformer-based-end-to |
| Repo | |
| Framework | |
Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
| Title | Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition |
| Authors | Shaoshi Ling, Yuzong Liu, Julian Salazar, Katrin Kirchhoff |
| Abstract | We propose a novel approach to semi-supervised automatic speech recognition (ASR). We first exploit a large amount of unlabeled audio data via representation learning, where we reconstruct a temporal slice of filterbank features from past and future context frames. The resulting deep contextualized acoustic representations (DeCoAR) are then used to train a CTC-based end-to-end ASR system using a smaller amount of labeled audio data. In our experiments, we show that systems trained on DeCoAR consistently outperform ones trained on conventional filterbank features, giving 42% and 19% relative improvement over the baseline on WSJ eval92 and LibriSpeech test-clean, respectively. Our approach can drastically reduce the amount of labeled data required; unsupervised training on LibriSpeech then supervision with 100 hours of labeled data achieves performance on par with training on all 960 hours directly. |
| Tasks | End-To-End Speech Recognition, Representation Learning, Speech Recognition |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01679v1 |
| https://arxiv.org/pdf/1912.01679v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-contextualized-acoustic-representations |
| Repo | |
| Framework | |
AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition
| Title | AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition |
| Authors | Yi-Chen Chen, Zhaojun Yang, Ching-Feng Yeh, Mahaveer Jain, Michael L. Seltzer |
| Abstract | As one of the major sources in speech variability, accents have posed a grand challenge to the robustness of speech recognition systems. In this paper, our goal is to build a unified end-to-end speech recognition system that generalizes well across accents. For this purpose, we propose a novel pre-training framework AIPNet based on generative adversarial nets (GAN) for accent-invariant representation learning: Accent Invariant Pre-training Networks. We pre-train AIPNet to disentangle accent-invariant and accent-specific characteristics from acoustic features through adversarial training on accented data for which transcriptions are not necessarily available. We further fine-tune AIPNet by connecting the accent-invariant module with an attention-based encoder-decoder model for multi-accent speech recognition. In the experiments, our approach is compared against four baselines including both accent-dependent and accent-independent models. Experimental results on 9 English accents show that the proposed approach outperforms all the baselines by 2.3 \sim 4.5% relative reduction on average WER when transcriptions are available in all accents and by 1.6 \sim 6.1% relative reduction when transcriptions are only available in US accent. |
| Tasks | End-To-End Speech Recognition, Representation Learning, Speech Recognition |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.11935v1 |
| https://arxiv.org/pdf/1911.11935v1.pdf | |
| PWC | https://paperswithcode.com/paper/aipnet-generative-adversarial-pre-training-of |
| Repo | |
| Framework | |
Independent language modeling architecture for end-to-end ASR
| Title | Independent language modeling architecture for end-to-end ASR |
| Authors | Van Tung Pham, Haihua Xu, Yerbolat Khassanov, Zhiping Zeng, Eng Siong Chng, Chongjia Ni, Bin Ma, Haizhou Li |
| Abstract | The attention-based end-to-end (E2E) automatic speech recognition (ASR) architecture allows for joint optimization of acoustic and language models within a single network. However, in a vanilla E2E ASR architecture, the decoder sub-network (subnet), which incorporates the role of the language model (LM), is conditioned on the encoder output. This means that the acoustic encoder and the language model are entangled that doesn’t allow language model to be trained separately from external text data. To address this problem, in this work, we propose a new architecture that separates the decoder subnet from the encoder output. In this way, the decoupled subnet becomes an independently trainable LM subnet, which can easily be updated using the external text data. We study two strategies for updating the new architecture. Experimental results show that, 1) the independent LM architecture benefits from external text data, achieving 9.3% and 22.8% relative character and word error rate reduction on Mandarin HKUST and English NSC datasets respectively; 2)the proposed architecture works well with external LM and can be generalized to different amount of labelled data. |
| Tasks | End-To-End Speech Recognition, Language Modelling, Speech Recognition |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1912.00863v1 |
| https://arxiv.org/pdf/1912.00863v1.pdf | |
| PWC | https://paperswithcode.com/paper/independent-language-modeling-architecture |
| Repo | |
| Framework | |
A holistic approach to polyphonic music transcription with neural networks
| Title | A holistic approach to polyphonic music transcription with neural networks |
| Authors | Miguel A. Román, Antonio Pertusa, Jorge Calvo-Zaragoza |
| Abstract | We present a framework based on neural networks to extract music scores directly from polyphonic audio in an end-to-end fashion. Most previous Automatic Music Transcription (AMT) methods seek a piano-roll representation of the pitches, that can be further transformed into a score by incorporating tempo estimation, beat tracking, key estimation or rhythm quantization. Unlike these methods, our approach generates music notation directly from the input audio in a single stage. For this, we use a Convolutional Recurrent Neural Network (CRNN) with Connectionist Temporal Classification (CTC) loss function which does not require annotated alignments of audio frames with the score rhythmic information. We trained our model using as input Haydn, Mozart, and Beethoven string quartets and Bach chorales synthesized with different tempos and expressive performances. The output is a textual representation of four-voice music scores based on **kern format. Although the proposed approach is evaluated in a simplified scenario, results show that this model can learn to transcribe scores directly from audio signals, opening a promising avenue towards complete AMT. |
| Tasks | Quantization |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12086v1 |
| https://arxiv.org/pdf/1910.12086v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-holistic-approach-to-polyphonic-music |
| Repo | |
| Framework | |
