Paper Group ANR 694
Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity. Duet at TREC 2019 Deep Learning Track. Efficient Online Quantum Generative Adversarial Learning Algorithms with Applications. Efficient Sample-based Neural Architecture Search with Learnable Predictor. Patch Refinement – Localized 3D Object Detection …
Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
| Title | Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity |
| Authors | Chongzhi Zhang, Aishan Liu, Xianglong Liu, Yitao Xu, Hang Yu, Yuqing Ma, Tianlin Li |
| Abstract | Deep neural networks (DNNs) are vulnerable to adversarial examples where inputs with imperceptible perturbations mislead DNNs to incorrect results. Despite the potential risk they bring, adversarial examples are also valuable for providing insights into the weakness and blind-spots of DNNs. Thus, the interpretability of a DNN in the adversarial setting aims to explain the rationale behind its decision-making process and makes deeper understanding which results in better practical applications. To address this issue, we try to explain adversarial robustness for deep models from a new perspective of neuron sensitivity which is measured by neuron behavior variation intensity against benign and adversarial examples. In this paper, we first draw the close connection between adversarial robustness and neuron sensitivities, as sensitive neurons make the most non-trivial contributions to model predictions in the adversarial setting. Based on that, we further propose to improve adversarial robustness by constraining the similarities of sensitive neurons between benign and adversarial examples which stabilizes the behaviors of sensitive neurons towards adversarial noises. Moreover, we demonstrate that state-of-the-art adversarial training methods improve model robustness by reducing neuron sensitivities which in turn confirms the strong connections between adversarial robustness and neuron sensitivity as well as the effectiveness of using sensitive neurons to build robust models. Extensive experiments on various datasets demonstrate that our algorithm effectively achieves excellent results. |
| Tasks | Decision Making |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.06978v2 |
| https://arxiv.org/pdf/1909.06978v2.pdf | |
| PWC | https://paperswithcode.com/paper/interpreting-and-improving-adversarial |
| Repo | |
| Framework | |
Duet at TREC 2019 Deep Learning Track
| Title | Duet at TREC 2019 Deep Learning Track |
| Authors | Bhaskar Mitra, Nick Craswell |
| Abstract | This report discusses three submissions based on the Duet architecture to the Deep Learning track at TREC 2019. For the document retrieval task, we adapt the Duet model to ingest a “multiple field” view of documents—we refer to the new architecture as Duet with Multiple Fields (DuetMF). A second submission combines the DuetMF model with other neural and traditional relevance estimators in a learning-to-rank framework and achieves improved performance over the DuetMF baseline. For the passage retrieval task, we submit a single run based on an ensemble of eight Duet models. |
| Tasks | Learning-To-Rank |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04471v1 |
| https://arxiv.org/pdf/1912.04471v1.pdf | |
| PWC | https://paperswithcode.com/paper/duet-at-trec-2019-deep-learning-track |
| Repo | |
| Framework | |
Efficient Online Quantum Generative Adversarial Learning Algorithms with Applications
| Title | Efficient Online Quantum Generative Adversarial Learning Algorithms with Applications |
| Authors | Yuxuan Du, Min-Hsiu Hsieh, Dacheng Tao |
| Abstract | The exploration of quantum algorithms that possess quantum advantages is a central topic in quantum computation and quantum information processing. One potential candidate in this area is quantum generative adversarial learning (QuGAL), which conceptually has exponential advantages over classical adversarial networks. However, the corresponding learning algorithm remains obscured. In this paper, we propose the first quantum generative adversarial learning algorithm– the quantum multiplicative matrix weight algorithm (QMMW)– which enables the efficient processing of fundamental tasks. The computational complexity of QMMW is polynomially proportional to the number of training rounds and logarithmically proportional to the input size. The core concept of the proposed algorithm combines QuGAL with online learning. We exploit the implementation of QuGAL with parameterized quantum circuits, and numerical experiments for the task of entanglement test for pure state are provided to support our claims. |
| Tasks | |
| Published | 2019-04-21 |
| URL | http://arxiv.org/abs/1904.09602v1 |
| http://arxiv.org/pdf/1904.09602v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-online-quantum-generative |
| Repo | |
| Framework | |
Efficient Sample-based Neural Architecture Search with Learnable Predictor
| Title | Efficient Sample-based Neural Architecture Search with Learnable Predictor |
| Authors | Han Shi, Renjie Pi, Hang Xu, Zhenguo Li, James T. Kwok, Tong Zhang |
| Abstract | Neural Architecture Search (NAS) has shown great potentials in finding a better neural network design than human design. Sample-based NAS is the most fundamental method aiming at exploring the search space and evaluating the most promising architecture. However, few works have focused on improving the sampling efficiency for NAS algorithm. For balancing exploitation and exploration, we propose BONAS (Bayesian Optimized Neural Architecture Search), a sample-based NAS framework combined with Bayesian Optimization. The main components of BONAS are Sampler and Learnable Embedding Extractor. Specifically, we apply Evolution Algorithm method as our sampler and apply Graph Convolutional Network predictor as a surrogate model to adaptively discover and incorporate nodes structure to approximate the performance of the architecture. For NAS-oriented tasks, we also design a weighted loss focusing on architectures with high performance. Extensive experiments are conducted to verify the effectiveness of our method over many competing methods, e.g. 123.7x more efficient than Random Search and 7.5x more efficient than previous SOTA LaNAS for finding the best architecture on the largest NAS data set NAS-Bench-101. |
| Tasks | Neural Architecture Search |
| Published | 2019-11-21 |
| URL | https://arxiv.org/abs/1911.09336v2 |
| https://arxiv.org/pdf/1911.09336v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-objective-neural-architecture-search-1 |
| Repo | |
| Framework | |
Patch Refinement – Localized 3D Object Detection
| Title | Patch Refinement – Localized 3D Object Detection |
| Authors | Johannes Lehner, Andreas Mitterecker, Thomas Adler, Markus Hofmarcher, Bernhard Nessler, Sepp Hochreiter |
| Abstract | We introduce Patch Refinement a two-stage model for accurate 3D object detection and localization from point cloud data. Patch Refinement is composed of two independently trained Voxelnet-based networks, a Region Proposal Network (RPN) and a Local Refinement Network (LRN). We decompose the detection task into a preliminary Bird’s Eye View (BEV) detection step and a local 3D detection step. Based on the proposed BEV locations by the RPN, we extract small point cloud subsets (“patches”), which are then processed by the LRN, which is less limited by memory constraints due to the small area of each patch. Therefore, we can apply encoding with a higher voxel resolution locally. The independence of the LRN enables the use of additional augmentation techniques and allows for an efficient, regression focused training as it uses only a small fraction of each scene. Evaluated on the KITTI 3D object detection benchmark, our submission from January 28, 2019, outperformed all previous entries on all three difficulties of the class car, using only 50 % of the available training data and only LiDAR information. |
| Tasks | 3D Object Detection, Object Detection |
| Published | 2019-10-09 |
| URL | https://arxiv.org/abs/1910.04093v1 |
| https://arxiv.org/pdf/1910.04093v1.pdf | |
| PWC | https://paperswithcode.com/paper/patch-refinement-localized-3d-object |
| Repo | |
| Framework | |
Multiple criteria hierarchy process for sorting problems under uncertainty applied to the evaluation of the operational maturity of research institutions
| Title | Multiple criteria hierarchy process for sorting problems under uncertainty applied to the evaluation of the operational maturity of research institutions |
| Authors | Renata Pelissari, Alvaro José Abackerli, Sarah Ben Amor, Maria Célia Oliveira, Kleber Manoel Infante |
| Abstract | Despite the availability of qualified research personnel, up-to-date research facilities and experience in developing applied research and innovation, many worldwide research institutions face difficulties when managing contracted Research and Development (R&D) projects due to expectations from Industry (private sector). Such difficulties have motivated funding agents to create evaluation processes to check whether the operational procedures of funded research institutions are sufficient to provide timely answers to demand for innovation from industry and also to identify aspects that require quality improvement in research development. For this purpose, several multiple criteria decision-making approaches can be applied. Among the available multiple criteria approaches, sorting methods are one prominent tool to evaluate the operational capacity. However, the first difficulty in applying multiple criteria sorting methods is the need to hierarchically structure multiple criteria in order to represent the intended decision process. Additional challenges include the elicitation of the preference information and the definition of criteria evaluation, since these are frequently affected by some imprecision. In this paper, a new sorting method is proposed to deal with all of those critical points simultaneously. To consider multiple levels for the decision criteria, the FlowSort method is extended to account for hierarchical criteria. To deal with imprecise data, the FlowSort is integrated with fuzzy approaches. To yield solutions that consider fluctuations from imprecise weights, the Stochastic Multicriteria Acceptability Analysis is used. Finally, the proposed method is applied to the evaluation of research institutions, classifying them according to their operational maturity for development of applied research. |
| Tasks | Decision Making |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.05324v1 |
| https://arxiv.org/pdf/1912.05324v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-criteria-hierarchy-process-for |
| Repo | |
| Framework | |
Shallow Art: Art Extension Through Simple Machine Learning
| Title | Shallow Art: Art Extension Through Simple Machine Learning |
| Authors | Kyle Robinson, Dan Brown |
| Abstract | Shallow Art presents, implements, and tests the use of simple single-output classification and regression models for the purpose of art generation. Various machine learning algorithms are trained on collections of computer generated images, artworks from Vincent van Gogh, and artworks from Rembrandt van Rijn. These models are then provided half of an image and asked to complete the missing side. The resulting images are displayed, and we explore implications for computational creativity. |
| Tasks | |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.11118v1 |
| https://arxiv.org/pdf/1910.11118v1.pdf | |
| PWC | https://paperswithcode.com/paper/shallow-art-art-extension-through-simple |
| Repo | |
| Framework | |
State of Compact Architecture Search For Deep Neural Networks
| Title | State of Compact Architecture Search For Deep Neural Networks |
| Authors | Mohammad Javad Shafiee, Andrew Hryniowski, Francis Li, Zhong Qiu Lin, Alexander Wong |
| Abstract | The design of compact deep neural networks is a crucial task to enable widespread adoption of deep neural networks in the real-world, particularly for edge and mobile scenarios. Due to the time-consuming and challenging nature of manually designing compact deep neural networks, there has been significant recent research interest into algorithms that automatically search for compact network architectures. A particularly interesting class of compact architecture search algorithms are those that are guided by baseline network architectures. Such algorithms have been shown to be significantly more computationally efficient than unguided methods. In this study, we explore the current state of compact architecture search for deep neural networks through both theoretical and empirical analysis of four different state-of-the-art compact architecture search algorithms: i) group lasso regularization, ii) variational dropout, iii) MorphNet, and iv) Generative Synthesis. We examine these methods in detail based on a number of different factors such as efficiency, effectiveness, and scalability. Furthermore, empirical evaluations are conducted to compare the efficacy of these compact architecture search algorithms across three well-known benchmark datasets. While by no means an exhaustive exploration, we hope that this study helps provide insights into the interesting state of this relatively new area of research in terms of diversity and real, tangible gains already achieved in architecture design improvements. Furthermore, the hope is that this study would help in pushing the conversation forward towards a deeper theoretical and empirical understanding where the research community currently stands in the landscape of compact architecture search for deep neural networks, and the practical challenges and considerations in leveraging such approaches for operational usage. |
| Tasks | |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.06466v1 |
| https://arxiv.org/pdf/1910.06466v1.pdf | |
| PWC | https://paperswithcode.com/paper/state-of-compact-architecture-search-for-deep |
| Repo | |
| Framework | |
Short note on the behavior of recurrent neural network for noisy dynamical system
| Title | Short note on the behavior of recurrent neural network for noisy dynamical system |
| Authors | Kyongmin Yeo |
| Abstract | The behavior of recurrent neural network for the data-driven simulation of noisy dynamical systems is studied by training a set of Long Short-Term Memory Networks (LSTM) on the Mackey-Glass time series with a wide range of noise level. It is found that, as the training noise becomes larger, LSTM learns to depend more on its autonomous dynamics than the noisy input data. As a result, LSTM trained on noisy data becomes less susceptible to the perturbation in the data, but has a longer relaxation timescale. On the other hand, when trained on noiseless data, LSTM becomes extremely sensitive to a small perturbation, but is able to adjusts to the changes in the input data. |
| Tasks | Time Series |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.05158v1 |
| http://arxiv.org/pdf/1904.05158v1.pdf | |
| PWC | https://paperswithcode.com/paper/short-note-on-the-behavior-of-recurrent |
| Repo | |
| Framework | |
Stochastic Bandits with Delay-Dependent Payoffs
| Title | Stochastic Bandits with Delay-Dependent Payoffs |
| Authors | Leonardo Cella, Nicolò Cesa-Bianchi |
| Abstract | Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled. After proving that finding an optimal policy is NP-hard even when all model parameters are known, we introduce a class of ranking policies provably approximating, to within a constant factor, the expected reward of the optimal policy. We show an algorithm whose regret with respect to the best ranking policy is bounded by $\widetilde{\mathcal{O}}\big(!\sqrt{kT}\big)$, where $k$ is the number of arms and $T$ is time. Our algorithm uses only $\mathcal{O}\big(k\ln\ln T\big)$ switches, which helps when switching between policies is costly. As constructing the class of learning policies requires ordering the arms according to their expectations, we also bound the number of pulls required to do so. Finally, we run experiments to compare our algorithm against UCB on different problem instances. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02757v4 |
| https://arxiv.org/pdf/1910.02757v4.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-bandits-with-delay-dependent |
| Repo | |
| Framework | |
Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation
| Title | Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation |
| Authors | Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon |
| Abstract | When a deep neural network is trained on data with only image-level labeling, the regions activated in each image tend to identify only a small region of the target object. We propose a method of using videos automatically harvested from the web to identify a larger region of the target object by using temporal information, which is not present in the static image. The temporal variations in a video allow different regions of the target object to be activated. We obtain an activated region in each frame of a video, and then aggregate the regions from successive frames into a single image, using a warping technique based on optical flow. The resulting localization maps cover more of the target object, and can then be used as proxy ground-truth to train a segmentation network. This simple approach outperforms existing methods under the same level of supervision, and even approaches relying on extra annotations. Based on VGG-16 and ResNet 101 backbones, our method achieves the mIoU of 65.0 and 67.4, respectively, on PASCAL VOC 2012 test images, which represents a new state-of-the-art. |
| Tasks | Optical Flow Estimation, Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.04501v1 |
| https://arxiv.org/pdf/1908.04501v1.pdf | |
| PWC | https://paperswithcode.com/paper/frame-to-frame-aggregation-of-active-regions |
| Repo | |
| Framework | |
StableNet: Semi-Online, Multi-Scale Deep Video Stabilization
| Title | StableNet: Semi-Online, Multi-Scale Deep Video Stabilization |
| Authors | Chia-Hung Huang, Hang Yin, Yu-Wing Tai, Chi-Keung Tang |
| Abstract | Video stabilization algorithms are of greater importance nowadays with the prevalence of hand-held devices which unavoidably produce videos with undesirable shaky motions. In this paper we propose a data-driven online video stabilization method along with a paired dataset for deep learning. The network processes each unsteady frame progressively in a multi-scale manner, from low resolution to high resolution, and then outputs an affine transformation to stabilize the frame. Different from conventional methods which require explicit feature tracking or optical flow estimation, the underlying stabilization process is learned implicitly from the training data, and the stabilization process can be done online. Since there are limited public video stabilization datasets available, we synthesized unstable videos with different extent of shake that simulate real-life camera movement. Experiments show that our method is able to outperform other stabilization methods in several unstable samples while remaining comparable in general. Also, our method is tested on complex contents and found robust enough to dampen these samples to some extent even it was not explicitly trained in the contents. |
| Tasks | Optical Flow Estimation |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10283v1 |
| https://arxiv.org/pdf/1907.10283v1.pdf | |
| PWC | https://paperswithcode.com/paper/stablenet-semi-online-multi-scale-deep-video |
| Repo | |
| Framework | |
Structured Knowledge Discovery from Massive Text Corpus
| Title | Structured Knowledge Discovery from Massive Text Corpus |
| Authors | Chenwei Zhang |
| Abstract | Nowadays, with the booming development of the Internet, people benefit from its convenience due to its open and sharing nature. A large volume of natural language texts is being generated by users in various forms, such as search queries, documents, and social media posts. As the unstructured text corpus is usually noisy and messy, it becomes imperative to correctly identify and accurately annotate structured information in order to obtain meaningful insights or better understand unstructured texts. On the other hand, the existing structured information, which embodies our knowledge such as entity or concept relations, often suffers from incompleteness or quality-related issues. Given a gigantic collection of texts which offers rich semantic information, it is also important to harness the massiveness of the unannotated text corpus to expand and refine existing structured knowledge with fewer annotation efforts. In this dissertation, I will introduce principles, models, and algorithms for effective structured knowledge discovery from the massive text corpus. We are generally interested in obtaining insights and better understanding unstructured texts with the help of structured annotations or by structure-aware modeling. Also, given the existing structured knowledge, we are interested in expanding its scale and improving its quality harnessing the massiveness of the text corpus. In particular, four problems are studied in this dissertation: Structured Intent Detection for Natural Language Understanding, Structure-aware Natural Language Modeling, Generative Structured Knowledge Expansion, and Synonym Refinement on Structured Knowledge. |
| Tasks | Intent Detection, Language Modelling |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1908.01837v1 |
| https://arxiv.org/pdf/1908.01837v1.pdf | |
| PWC | https://paperswithcode.com/paper/structured-knowledge-discovery-from-massive |
| Repo | |
| Framework | |
Improving Zero-shot Translation with Language-Independent Constraints
| Title | Improving Zero-shot Translation with Language-Independent Constraints |
| Authors | Ngoc-Quan Pham, Jan Niehues, Thanh-Le Ha, Alex Waibel |
| Abstract | An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an alternative to pivot translation which also allows us to better understand how the model captures information between languages. In this work, we carried out an investigation on this capability of the multilingual NMT models. First, we intentionally create an encoder architecture which is independent with respect to the source language. Such experiments shed light on the ability of NMT encoders to learn multilingual representations, in general. Based on such proof of concept, we were able to design regularization methods into the standard Transformer model, so that the whole architecture becomes more robust in zero-shot conditions. We investigated the behaviour of such models on the standard IWSLT 2017 multilingual dataset. We achieved an average improvement of 2.23 BLEU points across 12 language pairs compared to the zero-shot performance of a state-of-the-art multilingual system. Additionally, we carry out further experiments in which the effect is confirmed even for language pairs with multiple intermediate pivots. |
| Tasks | Machine Translation |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08584v1 |
| https://arxiv.org/pdf/1906.08584v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-zero-shot-translation-with-language |
| Repo | |
| Framework | |
RL-LIM: Reinforcement Learning-based Locally Interpretable Modeling
| Title | RL-LIM: Reinforcement Learning-based Locally Interpretable Modeling |
| Authors | Jinsung Yoon, Sercan O. Arik, Tomas Pfister |
| Abstract | Understanding black-box machine learning models is important towards their widespread adoption. However, developing globally interpretable models that explain the behavior of the entire model is challenging. An alternative approach is to explain black-box models through explaining individual prediction using a locally interpretable model. In this paper, we propose a novel method for locally interpretable modeling - Reinforcement Learning-based Locally Interpretable Modeling (RL-LIM). RL-LIM employs reinforcement learning to select a small number of samples and distill the black-box model prediction into a low-capacity locally interpretable model. Training is guided with a reward that is obtained directly by measuring agreement of the predictions from the locally interpretable model with the black-box model. RL-LIM near-matches the overall prediction performance of black-box models while yielding human-like interpretability, and significantly outperforms state of the art locally interpretable models in terms of overall prediction performance and fidelity. |
| Tasks | |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1909.12367v1 |
| https://arxiv.org/pdf/1909.12367v1.pdf | |
| PWC | https://paperswithcode.com/paper/rl-lim-reinforcement-learning-based-locally |
| Repo | |
| Framework | |
