Paper Group ANR 346
A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers. A Deep Learning approach for Hindi Named Entity Recognition. Experimental Demonstration of Learned Time-Domain Digital Back-Propagation. Experience Sharing Between Cooperative Reinforcement Learning Agents. Perturbed-History Exploration in Stochastic Linear Bandits. …
A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers
| Title | A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers |
| Authors | Junjie Cao, Zi Lin, Weiwei Sun, Xiaojun Wan |
| Abstract | We present a phenomenon-oriented comparative analysis of the two dominant approaches in task-independent semantic parsing: classic, knowledge-intensive and neural, data-intensive models. To reflect state-of-the-art neural NLP technologies, we introduce a new target structure-centric parser that can produce semantic graphs much more accurately than previous data-driven parsers. We then show that, in spite of comparable performance overall, knowledge- and data-intensive models produce different types of errors, in a way that can be explained by their theoretical properties. This analysis leads to new directions for parser development. |
| Tasks | Semantic Parsing |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02298v2 |
| https://arxiv.org/pdf/1907.02298v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparative-analysis-of-knowledge-intensive |
| Repo | |
| Framework | |
A Deep Learning approach for Hindi Named Entity Recognition
| Title | A Deep Learning approach for Hindi Named Entity Recognition |
| Authors | Bansi Shah, Sunil Kumar Kopparapu |
| Abstract | Named Entity Recognition is one of the most important text processing requirement in many NLP tasks. In this paper we use a deep architecture to accomplish the task of recognizing named entities in a given Hindi text sentence. Bidirectional Long Short Term Memory (BiLSTM) based techniques have been used for NER task in literature. In this paper, we first tune BiLSTM low-resource scenario to work for Hindi NER and propose two enhancements namely (a) de-noising auto-encoder (DAE) LSTM and (b) conditioning LSTM which show improvement in NER task compared to the BiLSTM approach. We use pre-trained word embedding to represent the words in the corpus, and the NER tags of the words are as defined by the used annotated corpora. Experiments have been performed to analyze the performance of different word embeddings and batch sizes which is essential for training deep models. |
| Tasks | Named Entity Recognition, Word Embeddings |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.01421v1 |
| https://arxiv.org/pdf/1911.01421v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-for-hindi-named |
| Repo | |
| Framework | |
Experimental Demonstration of Learned Time-Domain Digital Back-Propagation
| Title | Experimental Demonstration of Learned Time-Domain Digital Back-Propagation |
| Authors | Eric Sillekens, Wenting Yi, Daniel Semrau, Alessandro Ottino, Boris Karanov, Sujie Zhou, Kevin Law, Jack Chen, Domanic Lavery, Lidia Galdino, Polina Bayvel, Robert I. Killey |
| Abstract | We present the first experimental demonstration of learned time-domain digital back-propagation (DBP), in 64-GBd dual-polarization 64-QAM signal transmission over 1014 km. Performance gains were comparable to those obtained with conventional, higher complexity, frequency-domain DBP. |
| Tasks | |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.12197v1 |
| https://arxiv.org/pdf/1912.12197v1.pdf | |
| PWC | https://paperswithcode.com/paper/experimental-demonstration-of-learned-time |
| Repo | |
| Framework | |
Experience Sharing Between Cooperative Reinforcement Learning Agents
| Title | Experience Sharing Between Cooperative Reinforcement Learning Agents |
| Authors | Lucas Oliveira Souza, Gabriel de Oliveira Ramos, Celia Ghedini Ralha |
| Abstract | The idea of experience sharing between cooperative agents naturally emerges from our understanding of how humans learn. Our evolution as a species is tightly linked to the ability to exchange learned knowledge with one another. It follows that experience sharing (ES) between autonomous and independent agents could become the key to accelerate learning in cooperative multiagent settings. We investigate if randomly selecting experiences to share can increase the performance of deep reinforcement learning agents, and propose three new methods for selecting experiences to accelerate the learning process. Firstly, we introduce Focused ES, which prioritizes unexplored regions of the state space. Secondly, we present Prioritized ES, in which temporal-difference error is used as a measure of priority. Finally, we devise Focused Prioritized ES, which combines both previous approaches. The methods are empirically validated in a control problem. While sharing randomly selected experiences between two Deep Q-Network agents shows no improvement over a single agent baseline, we show that the proposed ES methods can successfully outperform the baseline. In particular, the Focused ES accelerates learning by a factor of 2, reducing by 51% the number of episodes required to complete the task. |
| Tasks | |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02191v1 |
| https://arxiv.org/pdf/1911.02191v1.pdf | |
| PWC | https://paperswithcode.com/paper/experience-sharing-between-cooperative |
| Repo | |
| Framework | |
Perturbed-History Exploration in Stochastic Linear Bandits
| Title | Perturbed-History Exploration in Stochastic Linear Bandits |
| Authors | Branislav Kveton, Csaba Szepesvari, Mohammad Ghavamzadeh, Craig Boutilier |
| Abstract | We propose a new online algorithm for minimizing the cumulative regret in stochastic linear bandits. The key idea is to build a perturbed history, which mixes the history of observed rewards with a pseudo-history of randomly generated i.i.d. pseudo-rewards. Our algorithm, perturbed-history exploration in a linear bandit (LinPHE), estimates a linear model from its perturbed history and pulls the arm with the highest value under that model. We prove a $\tilde{O}(d \sqrt{n})$ gap-free bound on the expected $n$-round regret of LinPHE, where $d$ is the number of features. Our analysis relies on novel concentration and anti-concentration bounds on the weighted sum of Bernoulli random variables. To show the generality of our design, we extend LinPHE to a logistic reward model. We evaluate both algorithms empirically and show that they are practical. |
| Tasks | |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.09132v1 |
| http://arxiv.org/pdf/1903.09132v1.pdf | |
| PWC | https://paperswithcode.com/paper/perturbed-history-exploration-in-stochastic-1 |
| Repo | |
| Framework | |
Improving Grounded Natural Language Understanding through Human-Robot Dialog
| Title | Improving Grounded Natural Language Understanding through Human-Robot Dialog |
| Authors | Jesse Thomason, Aishwarya Padmakumar, Jivko Sinapov, Nick Walker, Yuqian Jiang, Harel Yedidsion, Justin Hart, Peter Stone, Raymond J. Mooney |
| Abstract | Natural language understanding for robotics can require substantial domain- and platform-specific engineering. For example, for mobile robots to pick-and-place objects in an environment to satisfy human commands, we can specify the language humans use to issue such commands, and connect concept words like red can to physical object properties. One way to alleviate this engineering for a new domain is to enable robots in human environments to adapt dynamically—continually learning new language constructions and perceptual concepts. In this work, we present an end-to-end pipeline for translating natural language commands to discrete robot actions, and use clarification dialogs to jointly improve language parsing and concept grounding. We train and evaluate this agent in a virtual setting on Amazon Mechanical Turk, and we transfer the learned agent to a physical robot platform to demonstrate it in the real world. |
| Tasks | |
| Published | 2019-03-01 |
| URL | http://arxiv.org/abs/1903.00122v1 |
| http://arxiv.org/pdf/1903.00122v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-grounded-natural-language |
| Repo | |
| Framework | |
Assessing differentially private deep learning with Membership Inference
| Title | Assessing differentially private deep learning with Membership Inference |
| Authors | Daniel Bernau, Philip-William Grassal, Jonas Robl, Florian Kerschbaum |
| Abstract | Releasing data in the form of trained neural networks with differential privacy promises meaningful anonymization. However, there is an inherent privacy-accuracy trade-off in differential privacy which is challenging to assess for non-privacy experts. Furthermore, local and central differential privacy mechanisms are available to either anonymize the training data or the learnt neural network, and the privacy parameter $\epsilon$ cannot be used to compare these two mechanisms. We propose to measure privacy through a black-box membership inference attack and compare the privacy-accuracy trade-off for different local and central differential privacy mechanisms. Furthermore, we need to evaluate whether differential privacy is a useful mechanism in practice since differential privacy will especially be used by data scientists if membership inference risk is lowered more than accuracy. We experiment with several datasets and show that neither local differential privacy nor central differential privacy yields a consistently better privacy-accuracy trade-off in all cases. We also show that the relative privacy-accuracy trade-off, instead of strictly declining linearly over $\epsilon$, is only favorable within a small interval. For this purpose we propose $\varphi$, a ratio expressing the relative privacy-accuracy trade-off. |
| Tasks | Inference Attack |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11328v3 |
| https://arxiv.org/pdf/1912.11328v3.pdf | |
| PWC | https://paperswithcode.com/paper/assessing-differentially-private-deep |
| Repo | |
| Framework | |
Neural-Guided Symbolic Regression with Asymptotic Constraints
| Title | Neural-Guided Symbolic Regression with Asymptotic Constraints |
| Authors | Li Li, Minjie Fan, Rishabh Singh, Patrick Riley |
| Abstract | Symbolic regression is a type of discrete optimization problem that involves searching expressions that fit given data points. In many cases, other mathematical constraints about the unknown expression not only provide more information beyond just values at some inputs, but also effectively constrain the search space. We identify the asymptotic constraints of leading polynomial powers as the function approaches zero and infinity as useful constraints and create a system to use them for symbolic regression. The first part of the system is a conditional production rule generating neural network which preferentially generates production rules to construct expressions with the desired leading powers, producing novel expressions outside the training domain. The second part, which we call Neural-Guided Monte Carlo Tree Search, uses the network during a search to find an expression that conforms to a set of data points and desired leading powers. Lastly, we provide an extensive experimental validation on thousands of target expressions showing the efficacy of our system compared to exiting methods for finding unknown functions outside of the training set. |
| Tasks | |
| Published | 2019-01-23 |
| URL | https://arxiv.org/abs/1901.07714v2 |
| https://arxiv.org/pdf/1901.07714v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-guided-symbolic-regression-with |
| Repo | |
| Framework | |
Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
| Title | Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability |
| Authors | Stacey Truex, Ling Liu, Mehmet Emre Gursoy, Wenqi Wei, Lei Yu |
| Abstract | Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique contributions. First, through MPLens, we demonstrate how membership inference attack methods can be leveraged in adversarial machine learning. Second, through MPLens, we highlight how the vulnerability of pre-trained models under membership inference attack is not uniform across all classes, particularly when the training data itself is skewed. We show that risk from membership inference attacks is routinely increased when models use skewed training data. Finally, we investigate the effectiveness of differential privacy as a mitigation technique against membership inference attacks. We discuss the trade-offs of implementing such a mitigation strategy with respect to the model complexity, the learning task complexity, the dataset complexity and the privacy parameter settings. Our empirical results reveal that (1) minority groups within skewed datasets display increased risk for membership inference and (2) differential privacy presents many challenging trade-offs as a mitigation technique to membership inference risk. |
| Tasks | Inference Attack |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09777v1 |
| https://arxiv.org/pdf/1911.09777v1.pdf | |
| PWC | https://paperswithcode.com/paper/effects-of-differential-privacy-and-data |
| Repo | |
| Framework | |
Quantifying (Hyper) Parameter Leakage in Machine Learning
| Title | Quantifying (Hyper) Parameter Leakage in Machine Learning |
| Authors | Vasisht Duddu, D. Vijay Rao |
| Abstract | Machine Learning models, extensively used for various multimedia applications, are offered to users as a blackbox service on the Cloud on a pay-per-query basis. Such blackbox models are commercially valuable to adversaries, making them vulnerable to extraction attacks to reverse engineer the proprietary model thereby violating the model privacy and Intellectual Property. Here, the adversary first extracts the model architecture or hyperparameters through side channel leakage, followed by stealing the functionality of the target model by training the reconstructed architecture on a synthetic dataset. While the attacks proposed in literature are empirical, there is a need for a theoretical framework to measure the information leaked under such extraction attacks. To this extent, in this work, we propose a novel probabilistic framework, Airavata, to estimate the information leakage in such model extraction attacks. This framework captures the fact that extracting the exact target model is difficult due to experimental uncertainty while inferring model hyperparameters and stochastic nature of training to steal the target model functionality. Specifically, we use Bayesian Networks to capture uncertainty in estimating the target model under various extraction attacks based on the subjective notion of probability. We validate the proposed framework under different adversary assumptions commonly adopted in literature to reason about the attack efficacy. This provides a practical tool to infer actionable details about extracting blackbox models and help identify the best attack combination which maximises the knowledge extracted (or information leaked) from the target model. |
| Tasks | Inference Attack |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14409v2 |
| https://arxiv.org/pdf/1910.14409v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantifying-hyper-parameter-leakage-in |
| Repo | |
| Framework | |
Multiple Sample Clustering
| Title | Multiple Sample Clustering |
| Authors | Xiang Wang, Tie Liu |
| Abstract | The clustering algorithms that view each object data as a single sample drawn from a certain distribution, Gaussian distribution, for example, has been a hot topic for decades. Many clustering algorithms: such as k-means and spectral clustering are proposed based on the single sample assumption. However, in real life, each input object can usually be the multiple samples drawn from a certain hidden distribution. The traditional clustering algorithms cannot handle such a situation. This calls for the multiple sample clustering algorithm. But the traditional multiple sample clustering algorithms can only handle scalar samples or samples from Gaussian distribution. This constrains the application field of multiple sample clustering algorithms. In this paper, we purpose a general framework for multiple sample clustering. Various algorithms can be generated by this framework. We apply two specific cases of this framework: Wasserstein distance version and Bhattacharyya distance version on both synthetic data and stock price data. The simulation results show that the sufficient statistic can greatly improve the clustering accuracy and stability. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09731v3 |
| https://arxiv.org/pdf/1910.09731v3.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-sample-clustering |
| Repo | |
| Framework | |
Robust and Undetectable White-Box Watermarks for Deep Neural Networks
| Title | Robust and Undetectable White-Box Watermarks for Deep Neural Networks |
| Authors | Tianhao Wang, Florian Kerschbaum |
| Abstract | Watermarking of deep neural networks (DNN) can enable their tracing once released by a data owner. In this paper we generalize white-box watermarking algorithms for DNNs, where the data owner needs white-box access to the model to extract the watermark, and attack and defend them using DNNs. White-box watermarking algorithms have the advantage that they do not impact the accuracy of the watermarked model. We demonstrate a new property inference attack using a DNN that can detect watermarking by any existing, manually designed algorithm regardless of training data set and model architecture. We then use a new training architecture and a further DNN to create a new white-box watermarking algorithm that does not impact accuracy, is undetectable and robust against moderate model transformation attacks. |
| Tasks | Inference Attack |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14268v2 |
| https://arxiv.org/pdf/1910.14268v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-and-undetectable-white-box-watermarks |
| Repo | |
| Framework | |
Multivariate Spatial Data Visualization: A Survey
| Title | Multivariate Spatial Data Visualization: A Survey |
| Authors | Xiangyang He, Yubo Tao, Qirui Wang, Hai Lin |
| Abstract | Multivariate spatial data plays an important role in computational science and engineering simulations. The potential features and hidden relationships in multivariate data can assist scientists to gain an in-depth understanding of a scientific process, verify a hypothesis and further discover a new physical or chemical law. In this paper, we present a comprehensive survey of the state-of-the-art techniques for multivariate spatial data visualization. We first introduce the basic concept and characteristics of multivariate spatial data, and describe three main tasks in multivariate data visualization: feature classification, fusion visualization, and correlation analysis. Finally, we prospect potential research topics for multivariate data visualization according to the current research. |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.11344v1 |
| https://arxiv.org/pdf/1908.11344v1.pdf | |
| PWC | https://paperswithcode.com/paper/multivariate-spatial-data-visualization-a |
| Repo | |
| Framework | |
Oops! Predicting Unintentional Action in Video
| Title | Oops! Predicting Unintentional Action in Video |
| Authors | Dave Epstein, Boyuan Chen, Carl Vondrick |
| Abstract | From just a short glance at a video, we can often tell whether a person’s action is intentional or not. Can we train a model to recognize this? We introduce a dataset of in-the-wild videos of unintentional action, as well as a suite of tasks for recognizing, localizing, and anticipating its onset. We train a supervised neural network as a baseline and analyze its performance compared to human consistency on the tasks. We also investigate self-supervised representations that leverage natural signals in our dataset, and show the effectiveness of an approach that uses the intrinsic speed of video to perform competitively with highly-supervised pretraining. However, a significant gap between machine and human performance remains. The project website is available at https://oops.cs.columbia.edu |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11206v1 |
| https://arxiv.org/pdf/1911.11206v1.pdf | |
| PWC | https://paperswithcode.com/paper/oops-predicting-unintentional-action-in-video |
| Repo | |
| Framework | |
Optimising Optimisers with Push GP
| Title | Optimising Optimisers with Push GP |
| Authors | Michael Lones |
| Abstract | This work uses Push GP to automatically design both local and population-based optimisers for continuous-valued problems. The optimisers are trained on a single function optimisation landscape, using random transformations to discourage overfitting. They are then tested for generality on larger versions of the same problem, and on other continuous-valued problems. In most cases, the optimisers generalise well to the larger problems. Surprisingly, some of them also generalise very well to previously unseen problems, outperforming existing general purpose optimisers such as CMA-ES. Analysis of the behaviour of the evolved optimisers indicates a range of interesting optimisation strategies that are not found within conventional optimisers, suggesting that this approach could be useful for discovering novel and effective forms of optimisation in an automated manner. |
| Tasks | |
| Published | 2019-10-02 |
| URL | https://arxiv.org/abs/1910.00945v1 |
| https://arxiv.org/pdf/1910.00945v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimising-optimisers-with-push-gp |
| Repo | |
| Framework | |
