Paper Group ANR 451
Caption Generation of Robot Behaviors based on Unsupervised Learning of Action Segments. A Deep Learning Approach to Behavior-Based Learner Modeling. Improving cross-lingual model transfer by chunking. Generating Sense Embeddings for Syntactic and Semantic Analogy for Portuguese. Robust Learning-Based Control via Bootstrapped Multiplicative Noise. …
Caption Generation of Robot Behaviors based on Unsupervised Learning of Action Segments
| Title | Caption Generation of Robot Behaviors based on Unsupervised Learning of Action Segments |
| Authors | Koichiro Yoshino, Kohei Wakimoto, Yuta Nishimura, Satoshi Nakamura |
| Abstract | Bridging robot action sequences and their natural language captions is an important task to increase explainability of human assisting robots in their recently evolving field. In this paper, we propose a system for generating natural language captions that describe behaviors of human assisting robots. The system describes robot actions by using robot observations; histories from actuator systems and cameras, toward end-to-end bridging between robot actions and natural language captions. Two reasons make it challenging to apply existing sequence-to-sequence models to this mapping: 1) it is hard to prepare a large-scale dataset for any kind of robots and their environment, and 2) there is a gap between the number of samples obtained from robot action observations and generated word sequences of captions. We introduced unsupervised segmentation based on K-means clustering to unify typical robot observation patterns into a class. This method makes it possible for the network to learn the relationship from a small amount of data. Moreover, we utilized a chunking method based on byte-pair encoding (BPE) to fill in the gap between the number of samples of robot action observations and words in a caption. We also applied an attention mechanism to the segmentation task. Experimental results show that the proposed model based on unsupervised learning can generate better descriptions than other methods. We also show that the attention mechanism did not work well in our low-resource setting. |
| Tasks | Chunking |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10066v1 |
| https://arxiv.org/pdf/2003.10066v1.pdf | |
| PWC | https://paperswithcode.com/paper/caption-generation-of-robot-behaviors-based |
| Repo | |
| Framework | |
A Deep Learning Approach to Behavior-Based Learner Modeling
| Title | A Deep Learning Approach to Behavior-Based Learner Modeling |
| Authors | Yuwei Tu, Weiyu Chen, Christopher G. Brinton |
| Abstract | The increasing popularity of e-learning has created demand for improving online education through techniques such as predictive analytics and content recommendations. In this paper, we study learner outcome predictions, i.e., predictions of how they will perform at the end of a course. We propose a novel Two Branch Decision Network for performance prediction that incorporates two important factors: how learners progress through the course and how the content progresses through the course. We combine clickstream features which log every action the learner takes while learning, and textual features which are generated through pre-trained GloVe word embeddings. To assess the performance of our proposed network, we collect data from a short online course designed for corporate training and evaluate both neural network and non-neural network based algorithms on it. Our proposed algorithm achieves 95.7% accuracy and 0.958 AUC score, which outperforms all other models. The results also indicate the combination of behavior features and text features are more predictive than behavior features only and neural network models are powerful in capturing the joint relationship between user behavior and course content. |
| Tasks | Word Embeddings |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.08328v1 |
| https://arxiv.org/pdf/2001.08328v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-to-behavior-based |
| Repo | |
| Framework | |
Improving cross-lingual model transfer by chunking
| Title | Improving cross-lingual model transfer by chunking |
| Authors | Ayan Das, Sudeshna Sarkar |
| Abstract | We present a shallow parser guided cross-lingual model transfer approach in order to address the syntactic differences between source and target languages more effectively. In this work, we assume the chunks or phrases in a sentence as transfer units in order to address the syntactic differences between the source and target languages arising due to the differences in ordering of words in the phrases and the ordering of phrases in a sentence separately. |
| Tasks | Chunking |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12097v1 |
| https://arxiv.org/pdf/2002.12097v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-cross-lingual-model-transfer-by |
| Repo | |
| Framework | |
Generating Sense Embeddings for Syntactic and Semantic Analogy for Portuguese
| Title | Generating Sense Embeddings for Syntactic and Semantic Analogy for Portuguese |
| Authors | Jessica Rodrigues da Silva, Helena de Medeiros Caseli |
| Abstract | Word embeddings are numerical vectors which can represent words or concepts in a low-dimensional continuous space. These vectors are able to capture useful syntactic and semantic information. The traditional approaches like Word2Vec, GloVe and FastText have a strict drawback: they produce a single vector representation per word ignoring the fact that ambiguous words can assume different meanings. In this paper we use techniques to generate sense embeddings and present the first experiments carried out for Portuguese. Our experiments show that sense vectors outperform traditional word vectors in syntactic and semantic analogy tasks, proving that the language resource generated here can improve the performance of NLP tasks in Portuguese. |
| Tasks | Word Embeddings |
| Published | 2020-01-21 |
| URL | https://arxiv.org/abs/2001.07574v1 |
| https://arxiv.org/pdf/2001.07574v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-sense-embeddings-for-syntactic-and |
| Repo | |
| Framework | |
Robust Learning-Based Control via Bootstrapped Multiplicative Noise
| Title | Robust Learning-Based Control via Bootstrapped Multiplicative Noise |
| Authors | Benjamin Gravell, Tyler Summers |
| Abstract | Despite decades of research and recent progress in adaptive control and reinforcement learning, there remains a fundamental lack of understanding in designing controllers that provide robustness to inherent non-asymptotic uncertainties arising from models estimated with finite, noisy data. We propose a robust adaptive control algorithm that explicitly incorporates such non-asymptotic uncertainties into the control design. The algorithm has three components: (1) a least-squares nominal model estimator; (2) a bootstrap resampling method that quantifies non-asymptotic variance of the nominal model estimate; and (3) a non-conventional robust control design method using an optimal linear quadratic regulator (LQR) with multiplicative noise. A key advantage of the proposed approach is that the system identification and robust control design procedures both use stochastic uncertainty representations, so that the actual inherent statistical estimation uncertainty directly aligns with the uncertainty the robust controller is being designed against. We show through numerical experiments that the proposed robust adaptive controller can significantly outperform the certainty equivalent controller on both expected regret and measures of regret risk. |
| Tasks | |
| Published | 2020-02-24 |
| URL | https://arxiv.org/abs/2002.10069v1 |
| https://arxiv.org/pdf/2002.10069v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-learning-based-control-via |
| Repo | |
| Framework | |
No-Regret and Incentive-Compatible Online Learning
| Title | No-Regret and Incentive-Compatible Online Learning |
| Authors | Rupert Freeman, David M. Pennock, Chara Podimata, Jennifer Wortman Vaughan |
| Abstract | We study online learning settings in which experts act strategically to maximize their influence on the learning algorithm’s predictions by potentially misreporting their beliefs about a sequence of binary events. Our goal is twofold. First, we want the learning algorithm to be no-regret with respect to the best fixed expert in hindsight. Second, we want incentive compatibility, a guarantee that each expert’s best strategy is to report his true beliefs about the realization of each event. To achieve this goal, we build on the literature on wagering mechanisms, a type of multi-agent scoring rule. We provide algorithms that achieve no regret and incentive compatibility for myopic experts for both the full and partial information settings. In experiments on datasets from FiveThirtyEight, our algorithms have regret comparable to classic no-regret algorithms, which are not incentive-compatible. Finally, we identify an incentive-compatible algorithm for forward-looking strategic agents that exhibits diminishing regret in practice. |
| Tasks | |
| Published | 2020-02-20 |
| URL | https://arxiv.org/abs/2002.08837v1 |
| https://arxiv.org/pdf/2002.08837v1.pdf | |
| PWC | https://paperswithcode.com/paper/no-regret-and-incentive-compatible-online |
| Repo | |
| Framework | |
AlignNet: A Unifying Approach to Audio-Visual Alignment
| Title | AlignNet: A Unifying Approach to Audio-Visual Alignment |
| Authors | Jianren Wang, Zhaoyuan Fang, Hang Zhao |
| Abstract | We present AlignNet, a model that synchronizes videos with reference audios under non-uniform and irregular misalignments. AlignNet learns the end-to-end dense correspondence between each frame of a video and an audio. Our method is designed according to simple and well-established principles: attention, pyramidal processing, warping, and affinity function. Together with the model, we release a dancing dataset Dance50 for training and evaluation. Qualitative, quantitative and subjective evaluation results on dance-music alignment and speech-lip alignment demonstrate that our method far outperforms the state-of-the-art methods. Project video and code are available at https://jianrenw.github.io/AlignNet. |
| Tasks | |
| Published | 2020-02-12 |
| URL | https://arxiv.org/abs/2002.05070v1 |
| https://arxiv.org/pdf/2002.05070v1.pdf | |
| PWC | https://paperswithcode.com/paper/alignnet-a-unifying-approach-to-audio-visual |
| Repo | |
| Framework | |
robROSE: A robust approach for dealing with imbalanced data in fraud detection
| Title | robROSE: A robust approach for dealing with imbalanced data in fraud detection |
| Authors | Bart Baesens, Sebastiaan Höppner, Irene Ortner, Tim Verdonck |
| Abstract | A major challenge when trying to detect fraud is that the fraudulent activities form a minority class which make up a very small proportion of the data set. In most data sets, fraud occurs in typically less than 0.5% of the cases. Detecting fraud in such a highly imbalanced data set typically leads to predictions that favor the majority group, causing fraud to remain undetected. We discuss some popular oversampling techniques that solve the problem of imbalanced data by creating synthetic samples that mimic the minority class. A frequent problem when analyzing real data is the presence of anomalies or outliers. When such atypical observations are present in the data, most oversampling techniques are prone to create synthetic samples that distort the detection algorithm and spoil the resulting analysis. A useful tool for anomaly detection is robust statistics, which aims to find the outliers by first fitting the majority of the data and then flagging data observations that deviate from it. In this paper, we present a robust version of ROSE, called robROSE, which combines several promising approaches to cope simultaneously with the problem of imbalanced data and the presence of outliers. The proposed method achieves to enhance the presence of the fraud cases while ignoring anomalies. The good performance of our new sampling technique is illustrated on simulated and real data sets and it is shown that robROSE can provide better insight in the structure of the data. The source code of the robROSE algorithm is made freely available. |
| Tasks | Anomaly Detection, Fraud Detection |
| Published | 2020-03-22 |
| URL | https://arxiv.org/abs/2003.11915v1 |
| https://arxiv.org/pdf/2003.11915v1.pdf | |
| PWC | https://paperswithcode.com/paper/robrose-a-robust-approach-for-dealing-with |
| Repo | |
| Framework | |
Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization
| Title | Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization |
| Authors | Zhize Li, Dmitry Kovalev, Xun Qian, Peter Richtárik |
| Abstract | Due to the high communication cost in distributed and federated learning problems, methods relying on compression of communicated messages are becoming increasingly popular. While in other contexts the best performing gradient-type methods invariably rely on some form of acceleration/momentum to reduce the number of iterations, there are no methods which combine the benefits of both gradient compression and acceleration. In this paper, we remedy this situation and propose the first accelerated compressed gradient descent (ACGD) methods. In the single machine regime, we prove that ACGD enjoys the rate $O\left((1+\omega)\sqrt{\frac{L}{\mu}}\log \frac{1}{\epsilon}\right)$ for $\mu$-strongly convex problems and $O\left((1+\omega)\sqrt{\frac{L}{\epsilon}}\right)$ for convex problems, respectively, where $L$ is the smoothness constant and $\omega$ is the compression parameter. Our results improve upon the existing non-accelerated rates $O\left((1+\omega)\frac{L}{\mu}\log \frac{1}{\epsilon}\right)$ and $O\left((1+\omega)\frac{L}{\epsilon}\right)$, respectively, and recover the optimal rates of accelerated gradient descent as a special case when no compression ($\omega=0$) is applied. We further propose a distributed variant of ACGD (called ADIANA) and prove the convergence rate $\widetilde{O}\left(\omega+\sqrt{\frac{L}{\mu}} +\sqrt{\left(\frac{\omega}{n}+\sqrt{\frac{\omega}{n}}\right)\frac{\omega L}{\mu}}\right)$, where $n$ is the number of devices/workers and $\widetilde{O}$ hides the logarithmic factor $\log \frac{1}{\epsilon}$. This improves upon the previous best result $\widetilde{O}\left(\omega + \frac{L}{\mu}+\frac{\omega L}{n\mu} \right)$ achieved by the DIANA method of Mishchenko et al (2019). Finally, we conduct several experiments on real-world datasets which corroborate our theoretical results and confirm the practical superiority of our methods. |
| Tasks | |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2002.11364v1 |
| https://arxiv.org/pdf/2002.11364v1.pdf | |
| PWC | https://paperswithcode.com/paper/acceleration-for-compressed-gradient-descent |
| Repo | |
| Framework | |
Automatic Pruning for Quantized Neural Networks
| Title | Automatic Pruning for Quantized Neural Networks |
| Authors | Luis Guerra, Bohan Zhuang, Ian Reid, Tom Drummond |
| Abstract | Neural network quantization and pruning are two techniques commonly used to reduce the computational complexity and memory footprint of these models for deployment. However, most existing pruning strategies operate on full-precision and cannot be directly applied to discrete parameter distributions after quantization. In contrast, we study a combination of these two techniques to achieve further network compression. In particular, we propose an effective pruning strategy for selecting redundant low-precision filters. Furthermore, we leverage Bayesian optimization to efficiently determine the pruning ratio for each layer. We conduct extensive experiments on CIFAR-10 and ImageNet with various architectures and precisions. In particular, for ResNet-18 on ImageNet, we prune 26.12% of the model size with Binarized Neural Network quantization, achieving a top-1 classification accuracy of 47.32% in a model of 2.47 MB and 59.30% with a 2-bit DoReFa-Net in 4.36 MB. |
| Tasks | Quantization |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00523v1 |
| https://arxiv.org/pdf/2002.00523v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-pruning-for-quantized-neural |
| Repo | |
| Framework | |
Stratified cross-validation for unbiased and privacy-preserving federated learning
| Title | Stratified cross-validation for unbiased and privacy-preserving federated learning |
| Authors | R. Bey, R. Goussault, M. Benchoufi, R. Porcher |
| Abstract | Large-scale collections of electronic records constitute both an opportunity for the development of more accurate prediction models and a threat for privacy. To limit privacy exposure new privacy-enhancing techniques are emerging such as federated learning which enables large-scale data analysis while avoiding the centralization of records in a unique database that would represent a critical point of failure. Although promising regarding privacy protection, federated learning prevents using some data-cleaning algorithms thus inducing new biases. In this work we focus on the recurrent problem of duplicated records that, if not handled properly, may cause over-optimistic estimations of a model’s performances. We introduce and discuss stratified cross-validation, a validation methodology that leverages stratification techniques to prevent data leakage in federated learning settings without relying on demanding deduplication algorithms. |
| Tasks | |
| Published | 2020-01-22 |
| URL | https://arxiv.org/abs/2001.08090v2 |
| https://arxiv.org/pdf/2001.08090v2.pdf | |
| PWC | https://paperswithcode.com/paper/stratified-cross-validation-for-unbiased-and |
| Repo | |
| Framework | |
Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits
| Title | Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits |
| Authors | Maegan Tucker, Myra Cheng, Ellen Novoseller, Richard Cheng, Yisong Yue, Joel W. Burdick, Aaron D. Ames |
| Abstract | Understanding users’ gait preferences of a lower-body exoskeleton requires optimizing over the high-dimensional gait parameter space. However, existing preference-based learning methods have only explored low-dimensional domains due to computational limitations. To learn user preferences in high dimensions, this work presents LineCoSpar, a human-in-the-loop preference-based framework that enables optimization over many parameters by iteratively exploring one-dimensional subspaces. Additionally, this work identifies gait attributes that characterize broader preferences across users. In simulations and human trials, we empirically verify that LineCoSpar is a sample-efficient approach for high-dimensional preference optimization. Our analysis of the experimental data reveals a correspondence between human preferences and objective measures of dynamic stability, while also highlighting inconsistencies in the utility functions underlying different users’ gait preferences. This has implications for exoskeleton gait synthesis, an active field with applications to clinical use and patient rehabilitation. |
| Tasks | |
| Published | 2020-03-13 |
| URL | https://arxiv.org/abs/2003.06495v1 |
| https://arxiv.org/pdf/2003.06495v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-preference-based-learning-for-high |
| Repo | |
| Framework | |
Reducing Geographic Performance Differential for Face Recognition
| Title | Reducing Geographic Performance Differential for Face Recognition |
| Authors | Martins Bruveris, Jochem Gietema, Pouria Mortazavian, Mohan Mahadevan |
| Abstract | As face recognition algorithms become more accurate and get deployed more widely, it becomes increasingly important to ensure that the algorithms work equally well for everyone. We study the geographic performance differentials-differences in false acceptance and false rejection rates across different countries-when comparing selfies against photos from ID documents. We show how to mitigate geographic performance differentials using sampling strategies despite large imbalances in the dataset. Using vanilla domain adaptation strategies to fine-tune a face recognition CNN on domain-specific doc-selfie data improves the performance of the model on such data, but, in the presence of imbalanced training data, also significantly increases the demographic bias. We then show how to mitigate this effect by employing sampling strategies to balance the training procedure. |
| Tasks | Domain Adaptation, Face Recognition |
| Published | 2020-02-27 |
| URL | https://arxiv.org/abs/2002.12093v1 |
| https://arxiv.org/pdf/2002.12093v1.pdf | |
| PWC | https://paperswithcode.com/paper/reducing-geographic-performance-differential |
| Repo | |
| Framework | |
CNNTOP: a CNN-based Trajectory Owner Prediction Method
| Title | CNNTOP: a CNN-based Trajectory Owner Prediction Method |
| Authors | Xucheng Luo, Shengyang Li, Yuxiang Peng |
| Abstract | Trajectory owner prediction is the basis for many applications such as personalized recommendation, urban planning. Although much effort has been put on this topic, the results archived are still not good enough. Existing methods mainly employ RNNs to model trajectories semantically due to the inherent sequential attribute of trajectories. However, these approaches are weak at Point of Interest (POI) representation learning and trajectory feature detection. Thus, the performance of existing solutions is far from the requirements of practical applications. In this paper, we propose a novel CNN-based Trajectory Owner Prediction (CNNTOP) method. Firstly, we connect all POI according to trajectories from all users. The result is a connected graph that can be used to generate more informative POI sequences than other approaches. Secondly, we employ the Node2Vec algorithm to encode each POI into a low-dimensional real value vector. Then, we transform each trajectory into a fixed-dimensional matrix, which is similar to an image. Finally, a CNN is designed to detect features and predict the owner of a given trajectory. The CNN can extract informative features from the matrix representations of trajectories by convolutional operations, Batch normalization, and $K$-max pooling operations. Extensive experiments on real datasets demonstrate that CNNTOP substantially outperforms existing solutions in terms of macro-Precision, macro-Recall, macro-F1, and accuracy. |
| Tasks | Representation Learning |
| Published | 2020-01-05 |
| URL | https://arxiv.org/abs/2001.01185v1 |
| https://arxiv.org/pdf/2001.01185v1.pdf | |
| PWC | https://paperswithcode.com/paper/cnntop-a-cnn-based-trajectory-owner |
| Repo | |
| Framework | |
Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training
| Title | Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training |
| Authors | Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi, Yoko Sasaki |
| Abstract | In this paper, we propose an automatic labeled sequential data generation pipeline for human segmentation and velocity estimation with point clouds. Considering the impact of deep neural networks, state-of-the-art network architectures have been proposed for human recognition using point clouds captured by Light Detection and Ranging (LiDAR). However, one disadvantage is that legacy datasets may only cover the image domain without providing important label information and this limitation has disturbed the progress of research to date. Therefore, we develop an automatic labeled sequential data generation pipeline, in which we can control any parameter or data generation environment with pixel-wise and per-frame ground truth segmentation and pixel-wise velocity information for human recognition. Our approach uses a precise human model and reproduces a precise motion to generate realistic artificial data. We present more than 7K video sequences which consist of 32 frames generated by the proposed pipeline. With the proposed sequence generator, we confirm that human segmentation performance is improved when using the video domain compared to when using the image domain. We also evaluate our data by comparing with data generated under different conditions. In addition, we estimate pedestrian velocity with LiDAR by only utilizing data generated by the proposed pipeline. |
| Tasks | |
| Published | 2020-03-11 |
| URL | https://arxiv.org/abs/2003.05093v1 |
| https://arxiv.org/pdf/2003.05093v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-based-human-segmentation-and |
| Repo | |
| Framework | |
