Paper Group ANR 151
An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation. Data Masking with Privacy Guarantees. Multi-Armed Bandit Strategies for Non-Stationary Reward Distributions and Delayed Feedback Processes. Dota 2 with Large Scale Deep Reinforcement Learning. Neural Network Architecture Search with Differentiable Cartesian Ge …
An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
| Title | An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation |
| Authors | Xiang Kong, Bohan Li, Graham Neubig, Eduard Hovy, Yiming Yang |
| Abstract | In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via sentiment labels. Our proposed model is based on the paradigm of conditional adversarial learning; the training of a sentiment-controlled dialogue generator is assisted by an adversarial discriminator which assesses the fluency and feasibility of the response generating from the dialogue history and a given sentiment label. Because of the flexibility of our framework, the generator could be a standard sequence-to-sequence (SEQ2SEQ) model or a more complicated one such as a conditional variational autoencoder-based SEQ2SEQ model. Experimental results using automatic and human evaluation both demonstrate that our proposed framework is able to generate both semantically reasonable and sentiment-controlled dialogue responses. |
| Tasks | Dialogue Generation |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.07129v1 |
| http://arxiv.org/pdf/1901.07129v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-adversarial-approach-to-high-quality |
| Repo | |
| Framework | |
Data Masking with Privacy Guarantees
| Title | Data Masking with Privacy Guarantees |
| Authors | Anh T. Pham, Shalini Ghosh, Vinod Yegneswaran |
| Abstract | We study the problem of data release with privacy, where data is made available with privacy guarantees while keeping the usability of the data as high as possible — this is important in health-care and other domains with sensitive data. In particular, we propose a method of masking the private data with privacy guarantee while ensuring that a classifier trained on the masked data is similar to the classifier trained on the original data, to maintain usability. We analyze the theoretical risks of the proposed method and the traditional input perturbation method. Results show that the proposed method achieves lower risk compared to the input perturbation, especially when the number of training samples gets large. We illustrate the effectiveness of the proposed method of data masking for privacy-sensitive learning on $12$ benchmark datasets. |
| Tasks | |
| Published | 2019-01-08 |
| URL | http://arxiv.org/abs/1901.02185v1 |
| http://arxiv.org/pdf/1901.02185v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-masking-with-privacy-guarantees |
| Repo | |
| Framework | |
Multi-Armed Bandit Strategies for Non-Stationary Reward Distributions and Delayed Feedback Processes
| Title | Multi-Armed Bandit Strategies for Non-Stationary Reward Distributions and Delayed Feedback Processes |
| Authors | Larkin Liu, Richard Downe, Joshua Reid |
| Abstract | A survey is performed of various Multi-Armed Bandit (MAB) strategies in order to examine their performance in circumstances exhibiting non-stationary stochastic reward functions in conjunction with delayed feedback. We run several MAB simulations to simulate an online eCommerce platform for grocery pick up, optimizing for product availability. In this work, we evaluate several popular MAB strategies, such as $\epsilon$-greedy, UCB1, and Thompson Sampling. We compare the respective performances of each MAB strategy in the context of regret minimization. We run the analysis in the scenario where the reward function is non-stationary. Furthermore, the process experiences delayed feedback, where the reward function is not immediately responsive to the arm played. We devise a new adaptive technique (AG1) tailored for non-stationary reward functions in the delayed feedback scenario. The results of the simulation show show superior performance in the context of regret minimization compared to traditional MAB strategies. |
| Tasks | |
| Published | 2019-02-22 |
| URL | https://arxiv.org/abs/1902.08593v3 |
| https://arxiv.org/pdf/1902.08593v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-armed-bandit-strategies-for-non |
| Repo | |
| Framework | |
Dota 2 with Large Scale Deep Reinforcement Learning
| Title | Dota 2 with Large Scale Deep Reinforcement Learning |
| Authors | Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemysław Dębiak, Christy Dennison, David Farhi, Quirin Fischer, Shariq Hashme, Chris Hesse, Rafal Józefowicz, Scott Gray, Catherine Olsson, Jakub Pachocki, Michael Petrov, Henrique Pondé de Oliveira Pinto, Jonathan Raiman, Tim Salimans, Jeremy Schlatter, Jonas Schneider, Szymon Sidor, Ilya Sutskever, Jie Tang, Filip Wolski, Susan Zhang |
| Abstract | On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game. The game of Dota 2 presents novel challenges for AI systems such as long time horizons, imperfect information, and complex, continuous state-action spaces, all challenges which will become increasingly central to more capable AI systems. OpenAI Five leveraged existing reinforcement learning techniques, scaled to learn from batches of approximately 2 million frames every 2 seconds. We developed a distributed training system and tools for continual training which allowed us to train OpenAI Five for 10 months. By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task. |
| Tasks | Dota 2 |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06680v1 |
| https://arxiv.org/pdf/1912.06680v1.pdf | |
| PWC | https://paperswithcode.com/paper/dota-2-with-large-scale-deep-reinforcement |
| Repo | |
| Framework | |
Neural Network Architecture Search with Differentiable Cartesian Genetic Programming for Regression
| Title | Neural Network Architecture Search with Differentiable Cartesian Genetic Programming for Regression |
| Authors | Marcus Märtens, Dario Izzo |
| Abstract | The ability to design complex neural network architectures which enable effective training by stochastic gradient descent has been the key for many achievements in the field of deep learning. However, developing such architectures remains a challenging and resourceintensive process full of trial-and-error iterations. All in all, the relation between the network topology and its ability to model the data remains poorly understood. We propose to encode neural networks with a differentiable variant of Cartesian Genetic Programming (dCGPANN) and present a memetic algorithm for architecture design: local searches with gradient descent learn the network parameters while evolutionary operators act on the dCGPANN genes shaping the network architecture towards faster learning. Studying a particular instance of such a learning scheme, we are able to improve the starting feed forward topology by learning how to rewire and prune links, adapt activation functions and introduce skip connections for chosen regression tasks. The evolved network architectures require less space for network parameters and reach, given the same amount of time, a significantly lower error on average. |
| Tasks | |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01939v1 |
| https://arxiv.org/pdf/1907.01939v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-architecture-search-with |
| Repo | |
| Framework | |
DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences
| Title | DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences |
| Authors | Neeraj Battan, Abbhinav Venkat, Avinash Sharma |
| Abstract | 3D Human Motion Indexing and Retrieval is an interesting problem due to the rise of several data-driven applications aimed at analyzing and/or re-utilizing 3D human skeletal data, such as data-driven animation, analysis of sports bio-mechanics, human surveillance etc. Spatio-temporal articulations of humans, noisy/missing data, different speeds of the same motion etc. make it challenging and several of the existing state of the art methods use hand-craft features along with optimization based or histogram based comparison in order to perform retrieval. Further, they demonstrate it only for very small datasets and few classes. We make a case for using a learned representation that should recognize the motion as well as enforce a discriminative ranking. To that end, we propose, a 3D human motion descriptor learned using a deep network. Our learned embedding is generalizable and applicable to real-world data - addressing the aforementioned challenges and further enables sub-motion searching in its embedding space using another network. Our model exploits the inter-class similarity using trajectory cues, and performs far superior in a self-supervised setting. State of the art results on all these fronts is shown on two large scale 3D human motion datasets - NTU RGB+D and HDM05. |
| Tasks | |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05750v3 |
| https://arxiv.org/pdf/1908.05750v3.pdf | |
| PWC | https://paperswithcode.com/paper/deephums-deep-human-motion-signature-for-3d |
| Repo | |
| Framework | |
Coresets for Clustering with Fairness Constraints
| Title | Coresets for Clustering with Fairness Constraints |
| Authors | Lingxiao Huang, Shaofeng H. -C. Jiang, Nisheeth K. Vishnoi |
| Abstract | In a recent work, [19] studied the following “fair” variants of classical clustering problems such as $k$-means and $k$-median: given a set of $n$ data points in $\mathbb{R}^d$ and a binary type associated to each data point, the goal is to cluster the points while ensuring that the proportion of each type in each cluster is roughly the same as its underlying proportion. Subsequent work has focused on either extending this setting to when each data point has multiple, non-disjoint sensitive types such as race and gender [6], or to address the problem that the clustering algorithms in the above work do not scale well. The main contribution of this paper is an approach to clustering with fairness constraints that involve multiple, non-disjoint types, that is also scalable. Our approach is based on novel constructions of coresets: for the $k$-median objective, we construct an $\varepsilon$-coreset of size $O(\Gamma k^2 \varepsilon^{-d})$ where $\Gamma$ is the number of distinct collections of groups that a point may belong to, and for the $k$-means objective, we show how to construct an $\varepsilon$-coreset of size $O(\Gamma k^3\varepsilon^{-d-1})$. The former result is the first known coreset construction for the fair clustering problem with the $k$-median objective, and the latter result removes the dependence on the size of the full dataset as in [39] and generalizes it to multiple, non-disjoint types. Plugging our coresets into existing algorithms for fair clustering such as [5] results in the fastest algorithms for several cases. Empirically, we assess our approach over the \textbf{Adult}, \textbf{Bank}, \textbf{Diabetes} and \textbf{Athlete} dataset, and show that the coreset sizes are much smaller than the full dataset. We also achieve a speed-up to recent fair clustering algorithms [5,6] by incorporating our coreset construction. |
| Tasks | |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08484v4 |
| https://arxiv.org/pdf/1906.08484v4.pdf | |
| PWC | https://paperswithcode.com/paper/coresets-for-clustering-with-fairness |
| Repo | |
| Framework | |
Robust Influence Maximization for Hyperparametric Models
| Title | Robust Influence Maximization for Hyperparametric Models |
| Authors | Dimitris Kalimeris, Gal Kaplun, Yaron Singer |
| Abstract | In this paper, we study the problem of robust influence maximization in the independent cascade model under a hyperparametric assumption. In social networks users influence and are influenced by individuals with similar characteristics and as such, they are associated with some features. A recent surging research direction in influence maximization focuses on the case where the edge probabilities on the graph are not arbitrary but are generated as a function of the features of the users and a global hyperparameter. We propose a model where the objective is to maximize the worst-case number of influenced users for any possible value of that hyperparameter. We provide theoretical results showing that proper robust solution in our model is NP-hard and an algorithm that achieves improper robust optimization. We make-use of sampling based techniques and of the renowned multiplicative weight updates algorithm. Additionally, we validate our method empirically and prove that it outperforms the state-of-the-art robust influence maximization techniques. |
| Tasks | |
| Published | 2019-03-09 |
| URL | https://arxiv.org/abs/1903.03746v2 |
| https://arxiv.org/pdf/1903.03746v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-influence-maximization-for |
| Repo | |
| Framework | |
MEMe: An Accurate Maximum Entropy Method for Efficient Approximations in Large-Scale Machine Learning
| Title | MEMe: An Accurate Maximum Entropy Method for Efficient Approximations in Large-Scale Machine Learning |
| Authors | Diego Granziol, Binxin Ru, Stefan Zohren, Xiaowen Doing, Michael Osborne, Stephen Roberts |
| Abstract | Efficient approximation lies at the heart of large-scale machine learning problems. In this paper, we propose a novel, robust maximum entropy algorithm, which is capable of dealing with hundreds of moments and allows for computationally efficient approximations. We showcase the usefulness of the proposed method, its equivalence to constrained Bayesian variational inference and demonstrate its superiority over existing approaches in two applications, namely, fast log determinant estimation and information-theoretic Bayesian optimisation. |
| Tasks | Bayesian Optimisation |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.01101v1 |
| https://arxiv.org/pdf/1906.01101v1.pdf | |
| PWC | https://paperswithcode.com/paper/meme-an-accurate-maximum-entropy-method-for |
| Repo | |
| Framework | |
MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
| Title | MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation |
| Authors | Chaofan Tao, Fengmao Lv, Lixin Duan, Min Wu |
| Abstract | How to effectively learn from unlabeled data from the target domain is crucial for domain adaptation, as it helps reduce the large performance gap due to domain shift or distribution change. In this paper, we propose an easy-to-implement method dubbed MiniMax Entropy Networks (MMEN) based on adversarial learning. Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples with the help of labeled source samples. Specifically, we set an unfair multi-class classifier named categorical discriminator, which classifies source samples accurately but be confused about the categories of target samples. The generator learns a common subspace that aligns the unlabeled samples based on the target pseudo-labels. For MMEN, we also provide theoretical explanations to show that the learning of feature alignment reduces domain mismatch at the category level. Experimental results on various benchmark datasets demonstrate the effectiveness of our method over existing state-of-the-art baselines. |
| Tasks | Domain Adaptation |
| Published | 2019-04-21 |
| URL | https://arxiv.org/abs/1904.09601v2 |
| https://arxiv.org/pdf/1904.09601v2.pdf | |
| PWC | https://paperswithcode.com/paper/minimax-entropy-network-learning-category |
| Repo | |
| Framework | |
CPM-sensitive AUC for CTR prediction
| Title | CPM-sensitive AUC for CTR prediction |
| Authors | Zhaocheng Liu, Guangxue Yin |
| Abstract | The prediction of click-through rate (CTR) is crucial for industrial applications, such as online advertising. AUC is a commonly used evaluation indicator for CTR models. For advertising platforms, online performance is generally evaluated by CPM. However, in practice, AUC often improves in offline evaluation, but online CPM does not. As a result, a huge waste of precious online traffic and human costs has been caused. This is because there is a gap between offline AUC and online CPM. AUC can only reflect the order on CTR, but it does not reflect the order of CTR*Bid. Moreover, the bids of different advertisements are different, so the loss of income caused by different reverse-order pair is also different. For this reason, we propose the CPM-sensitive AUC (csAUC) to solve all these problems. We also give the csAUC calculation method based on dynamic programming. It can fully support the calculation of csAUC on large-scale data in real-world applications. |
| Tasks | Click-Through Rate Prediction |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.10272v1 |
| http://arxiv.org/pdf/1904.10272v1.pdf | |
| PWC | https://paperswithcode.com/paper/cpm-sensitive-auc-for-ctr-prediction |
| Repo | |
| Framework | |
A Framework for Model Search Across Multiple Machine Learning Implementations
| Title | A Framework for Model Search Across Multiple Machine Learning Implementations |
| Authors | Yoshiki Takahashi, Masato Asahara, Kazuyuki Shudo |
| Abstract | Several recently devised machine learning (ML) algorithms have shown improved accuracy for various predictive problems. Model searches, which explore to find an optimal ML algorithm and hyperparameter values for the target problem, play a critical role in such improvements. During a model search, data scientists typically use multiple ML implementations to construct several predictive models; however, it takes significant time and effort to employ multiple ML implementations due to the need to learn how to use them, prepare input data in several different formats, and compare their outputs. Our proposed framework addresses these issues by providing simple and unified coding method. It has been designed with the following two attractive features: i) new machine learning implementations can be added easily via common interfaces between the framework and ML implementations and ii) it can be scaled to handle large model configuration search spaces via profile-based scheduling. The results of our evaluation indicate that, with our framework, implementers need only write 55-144 lines of code to add a new ML implementation. They also show that ours was the fastest framework for the HIGGS dataset, and the second-fastest for the SECOM dataset. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10310v1 |
| https://arxiv.org/pdf/1908.10310v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-framework-for-model-search-across-multiple |
| Repo | |
| Framework | |
Saliency detection for seismic applications using multi-dimensional spectral projections and directional comparisons
| Title | Saliency detection for seismic applications using multi-dimensional spectral projections and directional comparisons |
| Authors | Muhammad Amir Shafiq, Zhiling Long, Tariq Alshawi, Ghassan AlRegib |
| Abstract | In this paper, we propose a novel approach for saliency detection for seismic applications using 3D-FFT local spectra and multi-dimensional plane projections. We develop a projection scheme by dividing a 3D-FFT local spectrum of a data volume into three distinct components, each depicting changes along a different dimension of the data. The saliency detection results obtained using each projected component are then combined to yield a saliency map. To accommodate the directional nature of seismic data, in this work, we modify the center-surround model, proven to be biologically plausible for visual attention, to incorporate directional comparisons around each voxel in a 3D volume. Experimental results on real seismic dataset from the F3 block in Netherlands offshore in the North Sea prove that the proposed algorithm is effective, efficient, and scalable. Furthermore, a subjective comparison of the results shows that it outperforms the state-of-the-art methods for saliency detection. |
| Tasks | Saliency Detection |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.11095v1 |
| http://arxiv.org/pdf/1901.11095v1.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-detection-for-seismic-applications |
| Repo | |
| Framework | |
DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors
| Title | DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors |
| Authors | Shuai Chen, Jinpeng Li, Chuanqi Yao, Wenbo Hou, Shuo Qin, Wenyao Jin, Xu Tang |
| Abstract | Traditional neural objection detection methods use multi-scale features that allow multiple detectors to perform detecting tasks independently and in parallel. At the same time, with the handling of the prior box, the algorithm’s ability to deal with scale invariance is enhanced. However, too many prior boxes and independent detectors will increase the computational redundancy of the detection algorithm. In this study, we introduce Dubox, a new one-stage approach that detects the objects without prior box. Working with multi-scale features, the designed dual scale residual unit makes dual scale detectors no longer run independently. The second scale detector learns the residual of the first. Dubox has enhanced the capacity of heuristic-guided that can further enable the first scale detector to maximize the detection of small targets and the second to detect objects that cannot be identified by the first one. Besides, for each scale detector, with the new classification-regression progressive strapped loss makes our process not based on prior boxes. Integrating these strategies, our detection algorithm has achieved excellent performance in terms of speed and accuracy. Extensive experiments on the VOC, COCO object detection benchmark have confirmed the effectiveness of this algorithm. |
| Tasks | Object Detection |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.06883v2 |
| http://arxiv.org/pdf/1904.06883v2.pdf | |
| PWC | https://paperswithcode.com/paper/dubox-no-prior-box-objection-detection-via |
| Repo | |
| Framework | |
Field-aware Neural Factorization Machine for Click-Through Rate Prediction
| Title | Field-aware Neural Factorization Machine for Click-Through Rate Prediction |
| Authors | Li Zhang, Weichen Shen, Shijian Li, Gang Pan |
| Abstract | Recommendation systems and computing advertisements have gradually entered the field of academic research from the field of commercial applications. Click-through rate prediction is one of the core research issues because the prediction accuracy affects the user experience and the revenue of merchants and platforms. Feature engineering is very important to improve click-through rate prediction. Traditional feature engineering heavily relies on people’s experience, and is difficult to construct a feature combination that can describe the complex patterns implied in the data. This paper combines traditional feature combination methods and deep neural networks to automate feature combinations to improve the accuracy of click-through rate prediction. We propose a mechannism named ‘Field-aware Neural Factorization Machine’ (FNFM). This model can have strong second order feature interactive learning ability like Field-aware Factorization Machine, on this basis, deep neural network is used for higher-order feature combination learning. Experiments show that the model has stronger expression ability than current deep learning feature combination models like the DeepFM, DCN and NFM. |
| Tasks | Click-Through Rate Prediction, Feature Engineering, Recommendation Systems |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09096v1 |
| http://arxiv.org/pdf/1902.09096v1.pdf | |
| PWC | https://paperswithcode.com/paper/field-aware-neural-factorization-machine-for |
| Repo | |
| Framework | |
