Paper Group ANR 737
DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense. Modular Semantics and Characteristics for Bipolar Weighted Argumentation Graphs. Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale. Neural Network Cognitive Engine for Autonomous and Distributed Underlay Dynamic Spectrum Access. RIn-Close_ …
DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense
| Title | DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense |
| Authors | Hang Zhou, Kejiang Chen, Weiming Zhang, Han Fang, Wenbo Zhou, Nenghai Yu |
| Abstract | Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose a Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points. In this paper, statistical outlier removal (SOR) and a data-driven upsampling network are considered as denoiser and upsampler respectively. Compared with baseline defenses, DUP-Net has three advantages. First, with DUP-Net as a defense, the target model is more robust to white-box adversarial attacks. Second, the statistical outlier removal provides added robustness since it is a non-differentiable denoising operation. Third, the upsampler network can be trained on a small dataset and defends well against adversarial attacks generated from other point cloud datasets. We conduct various experiments to validate that DUP-Net is very effective as defense in practice. Our best defense eliminates 83.8% of C&W and l_2 loss based attack (point shifting), 50.0% of C&W and Hausdorff distance loss based attack (point adding) and 9.0% of saliency map based attack (point dropping) under 200 dropped points on PointNet. |
| Tasks | Denoising |
| Published | 2018-12-25 |
| URL | https://arxiv.org/abs/1812.11017v2 |
| https://arxiv.org/pdf/1812.11017v2.pdf | |
| PWC | https://paperswithcode.com/paper/deflecting-3d-adversarial-point-clouds |
| Repo | |
| Framework | |
Modular Semantics and Characteristics for Bipolar Weighted Argumentation Graphs
| Title | Modular Semantics and Characteristics for Bipolar Weighted Argumentation Graphs |
| Authors | Till Mossakowski, Fabian Neuhaus |
| Abstract | This paper addresses the semantics of weighted argumentation graphs that are bipolar, i.e. contain both attacks and supports for arguments. It builds on previous work by Amgoud, Ben-Naim et. al. We study the various characteristics of acceptability semantics that have been introduced in these works, and introduce the notion of a modular acceptability semantics. A semantics is modular if it cleanly separates aggregation of attacking and supporting arguments (for a given argument $a$) from the computation of their influence on $a$'s initial weight. We show that the various semantics for bipolar argumentation graphs from the literature may be analysed as a composition of an aggregation function with an influence function. Based on this modular framework, we prove general convergence and divergence theorems. We demonstrate that all well-behaved modular acceptability semantics converge for all acyclic graphs and that no sum-based semantics can converge for all graphs. In particular, we show divergence of Euler-based semantics (Amgoud et al.) for certain cyclic graphs. Further, we provide the first semantics for bipolar weighted graphs that converges for all graphs. |
| Tasks | |
| Published | 2018-07-17 |
| URL | http://arxiv.org/abs/1807.06685v2 |
| http://arxiv.org/pdf/1807.06685v2.pdf | |
| PWC | https://paperswithcode.com/paper/modular-semantics-and-characteristics-for |
| Repo | |
| Framework | |
Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale
| Title | Snorkel DryBell: A Case Study in Deploying Weak Supervision at Industrial Scale |
| Authors | Stephen H. Bach, Daniel Rodriguez, Yintao Liu, Chong Luo, Haidong Shao, Cassandra Xia, Souvik Sen, Alexander Ratner, Braden Hancock, Houman Alborzi, Rahul Kuchhal, Christopher Ré, Rob Malkin |
| Abstract | Labeling training data is one of the most costly bottlenecks in developing machine learning-based applications. We present a first-of-its-kind study showing how existing knowledge resources from across an organization can be used as weak supervision in order to bring development time and cost down by an order of magnitude, and introduce Snorkel DryBell, a new weak supervision management system for this setting. Snorkel DryBell builds on the Snorkel framework, extending it in three critical aspects: flexible, template-based ingestion of diverse organizational knowledge, cross-feature production serving, and scalable, sampling-free execution. On three classification tasks at Google, we find that Snorkel DryBell creates classifiers of comparable quality to ones trained with tens of thousands of hand-labeled examples, converts non-servable organizational resources to servable models for an average 52% performance improvement, and executes over millions of data points in tens of minutes. |
| Tasks | |
| Published | 2018-12-02 |
| URL | https://arxiv.org/abs/1812.00417v2 |
| https://arxiv.org/pdf/1812.00417v2.pdf | |
| PWC | https://paperswithcode.com/paper/snorkel-drybell-a-case-study-in-deploying |
| Repo | |
| Framework | |
Neural Network Cognitive Engine for Autonomous and Distributed Underlay Dynamic Spectrum Access
| Title | Neural Network Cognitive Engine for Autonomous and Distributed Underlay Dynamic Spectrum Access |
| Authors | Fatemeh Shah-Mohammadi, Andres Kwasinski |
| Abstract | Two key challenges in underlay dynamic spectrum access (DSA) are how to establish an interference limit from the primary network (PN) and how cognitive radios (CRs) in the secondary network (SN) become aware of the interference they create on the PN, especially when there is no exchange of information between the two networks. These challenges are addressed in this paper by presenting a fully autonomous and distributed underlay DSA scheme where each CR operates based on predicting its transmission effect on the PN. The scheme is based on a cognitive engine with an artificial neural network that predicts, without exchanging information between the networks, the adaptive modulation and coding configuration for the primary link nearest to a transmitting CR. By managing the effect of the SN on the PN, the presented technique maintains the relative average throughput change in the PN within a prescribed maximum value, while also finding transmit settings for the CRs that result in throughput as large as allowed by the PN interference limit. It is shown through simulation results that the ability of the cognitive engine to estimate the effect of a CR transmission on the full adaptive modulation and coding (AMC) mode that is used at a PN link translates into a much more fine underlay transmit power control and increase of the CR transmission opportunities, compared to a scheme that can only estimate the modulation scheme used at the PN link. |
| Tasks | |
| Published | 2018-06-28 |
| URL | https://arxiv.org/abs/1806.11038v4 |
| https://arxiv.org/pdf/1806.11038v4.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-cognitive-engine-for |
| Repo | |
| Framework | |
RIn-Close_CVC2: an even more efficient enumerative algorithm for biclustering of numerical datasets
| Title | RIn-Close_CVC2: an even more efficient enumerative algorithm for biclustering of numerical datasets |
| Authors | Rosana Veroneze, Fernando J. Von Zuben |
| Abstract | RIn-Close_CVC is an efficient (take polynomial time per bicluster), complete (find all maximal biclusters), correct (all biclusters attend the user-defined level of consistency) and non-redundant (all the obtained biclusters are maximal and the same bicluster is not enumerated more than once) enumerative algorithm for mining maximal biclusters with constant values on columns in numerical datasets. Despite RIn-Close_CVC has all these outstanding properties, it has a high computational cost in terms of memory usage because it must keep a symbol table in memory to prevent a maximal bicluster to be found more than once. In this paper, we propose a new version of RIn-Close_CVC, named RIn-Close_CVC2, that does not use a symbol table to prevent redundant biclusters, and keeps all these four properties. We also prove that these algorithms actually possess these properties. Experiments are carried out with synthetic and real-world datasets to compare RIn-Close_CVC and RIn-Close_CVC2 in terms of memory usage and runtime. The experimental results show that RIn-Close_CVC2 brings a large reduction in memory usage and, in average, significant runtime gain when compared to its predecessor. |
| Tasks | |
| Published | 2018-10-17 |
| URL | http://arxiv.org/abs/1810.07725v1 |
| http://arxiv.org/pdf/1810.07725v1.pdf | |
| PWC | https://paperswithcode.com/paper/rin-close_cvc2-an-even-more-efficient |
| Repo | |
| Framework | |
Informative Gene Selection for Microarray Classification via Adaptive Elastic Net with Conditional Mutual Information
| Title | Informative Gene Selection for Microarray Classification via Adaptive Elastic Net with Conditional Mutual Information |
| Authors | Xin-Guang Yang, Yongjin Lu |
| Abstract | Due to the advantage of achieving a better performance under weak regularization, elastic net has attracted wide attention in statistics, machine learning, bioinformatics, and other fields. In particular, a variation of the elastic net, adaptive elastic net (AEN), integrates the adaptive grouping effect. In this paper, we aim to develop a new algorithm: Adaptive Elastic Net with Conditional Mutual Information (AEN-CMI) that further improves AEN by incorporating conditional mutual information into the gene selection process. We apply this new algorithm to screen significant genes for two kinds of cancers: colon cancer and leukemia. Compared with other algorithms including Support Vector Machine, Classic Elastic Net and Adaptive Elastic Net, the proposed algorithm, AEN-CMI, obtains the best classification performance using the least number of genes. |
| Tasks | |
| Published | 2018-06-05 |
| URL | http://arxiv.org/abs/1806.01466v3 |
| http://arxiv.org/pdf/1806.01466v3.pdf | |
| PWC | https://paperswithcode.com/paper/informative-gene-selection-for-microarray |
| Repo | |
| Framework | |
Maximal Jacobian-based Saliency Map Attack
| Title | Maximal Jacobian-based Saliency Map Attack |
| Authors | Rey Wiyatno, Anqi Xu |
| Abstract | The Jacobian-based Saliency Map Attack is a family of adversarial attack methods for fooling classification models, such as deep neural networks for image classification tasks. By saturating a few pixels in a given image to their maximum or minimum values, JSMA can cause the model to misclassify the resulting adversarial image as a specified erroneous target class. We propose two variants of JSMA, one which removes the requirement to specify a target class, and another that additionally does not need to specify whether to only increase or decrease pixel intensities. Our experiments highlight the competitive speeds and qualities of these variants when applied to datasets of hand-written digits and natural scenes. |
| Tasks | Adversarial Attack, Image Classification |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07945v1 |
| http://arxiv.org/pdf/1808.07945v1.pdf | |
| PWC | https://paperswithcode.com/paper/maximal-jacobian-based-saliency-map-attack |
| Repo | |
| Framework | |
Optimal Bipartite Network Clustering
| Title | Optimal Bipartite Network Clustering |
| Authors | Zhixin Zhou, Arash A. Amini |
| Abstract | We study bipartite community detection in networks, or more generally the network biclustering problem. We present a fast two-stage procedure based on spectral initialization followed by the application of a pseudo-likelihood classifier twice. Under mild regularity conditions, we establish the weak consistency of the procedure (i.e., the convergence of the misclassification rate to zero) under a general bipartite stochastic block model. We show that the procedure is optimal in the sense that it achieves the optimal convergence rate that is achievable by a biclustering oracle, adaptively over the whole class, up to constants. This is further formalized by deriving a minimax lower bound over a class of biclustering problems. The optimal rate we obtain sharpens some of the existing results and generalizes others to a wide regime of average degree growth, from sparse networks with average degrees growing arbitrarily slowly to fairly dense networks with average degrees of order $\sqrt{n}$. As a special case, we recover the known exact recovery threshold in the $\log n$ regime of sparsity. To obtain the consistency result, as part of the provable version of the algorithm, we introduce a sub-block partitioning scheme that is also computationally attractive, allowing for distributed implementation of the algorithm without sacrificing optimality. The provable algorithm is derived from a general class of pseudo-likelihood biclustering algorithms that employ simple EM type updates. We show the effectiveness of this general class by numerical simulations. |
| Tasks | Community Detection |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.06031v2 |
| http://arxiv.org/pdf/1803.06031v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-bipartite-network-clustering |
| Repo | |
| Framework | |
STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification
| Title | STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification |
| Authors | Yang Fu, Xiaoyang Wang, Yunchao Wei, Thomas Huang |
| Abstract | In this work, we propose a novel Spatial-Temporal Attention (STA) approach to tackle the large-scale person re-identification task in videos. Different from the most existing methods, which simply compute representations of video clips using frame-level aggregation (e.g. average pooling), the proposed STA adopts a more effective way for producing robust clip-level feature representation. Concretely, our STA fully exploits those discriminative parts of one target person in both spatial and temporal dimensions, which results in a 2-D attention score matrix via inter-frame regularization to measure the importances of spatial parts across different frames. Thus, a more robust clip-level feature representation can be generated according to a weighted sum operation guided by the mined 2-D attention score matrix. In this way, the challenging cases for video-based person re-identification such as pose variation and partial occlusion can be well tackled by the STA. We conduct extensive experiments on two large-scale benchmarks, i.e. MARS and DukeMTMC-VideoReID. In particular, the mAP reaches 87.7% on MARS, which significantly outperforms the state-of-the-arts with a large margin of more than 11.6%. |
| Tasks | Large-Scale Person Re-Identification, Person Re-Identification, Video-Based Person Re-Identification |
| Published | 2018-11-09 |
| URL | http://arxiv.org/abs/1811.04129v1 |
| http://arxiv.org/pdf/1811.04129v1.pdf | |
| PWC | https://paperswithcode.com/paper/sta-spatial-temporal-attention-for-large |
| Repo | |
| Framework | |
An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
| Title | An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification |
| Authors | Paul Marchwica, Michael Jamieson, Parthipan Siva |
| Abstract | In recent years, a variety of proposed methods based on deep convolutional neural networks (CNNs) have improved the state of the art for large-scale person re-identification (ReID). While a large number of optimizations and network improvements have been proposed, there has been relatively little evaluation of the influence of training data and baseline network architecture. In particular, it is usually assumed either that networks are trained on labeled data from the deployment location (scene-dependent), or else adapted with unlabeled data, both of which complicate system deployment. In this paper, we investigate the feasibility of achieving scene-independent person ReID by forming a large composite dataset for training. We present an in-depth comparison of several CNN baseline architectures for both scene-dependent and scene-independent ReID, across a range of training dataset sizes. We show that scene-independent ReID can produce leading-edge results, competitive with unsupervised domain adaption techniques. Finally, we introduce a new dataset for comparing within-camera and across-camera person ReID. |
| Tasks | Domain Adaptation, Large-Scale Person Re-Identification, Person Re-Identification |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06086v1 |
| http://arxiv.org/pdf/1805.06086v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-evaluation-of-deep-cnn-baselines-for-scene |
| Repo | |
| Framework | |
Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
| Title | Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts |
| Authors | Can Xu, Wei Wu, Yu Wu |
| Abstract | We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat. To imitate human behavior, we propose managing the flow of human-machine interactions with the dialogue acts as policies. The policies and response generation are jointly learned from human-human conversations, and the former is further optimized with a reinforcement learning approach. With the dialogue acts, we achieve significant improvement over state-of-the-art methods on response quality for given contexts and dialogue length in both machine-machine simulation and human-machine conversation. |
| Tasks | Dialogue Generation |
| Published | 2018-07-19 |
| URL | http://arxiv.org/abs/1807.07255v2 |
| http://arxiv.org/pdf/1807.07255v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-explainable-and-controllable-open |
| Repo | |
| Framework | |
Brenier approach for optimal transportation between a quasi-discrete measure and a discrete measure
| Title | Brenier approach for optimal transportation between a quasi-discrete measure and a discrete measure |
| Authors | Ying Lu, Liming Chen, Alexandre Saidi, Xianfeng Gu |
| Abstract | Correctly estimating the discrepancy between two data distributions has always been an important task in Machine Learning. Recently, Cuturi proposed the Sinkhorn distance which makes use of an approximate Optimal Transport cost between two distributions as a distance to describe distribution discrepancy. Although it has been successfully adopted in various machine learning applications (e.g. in Natural Language Processing and Computer Vision) since then, the Sinkhorn distance also suffers from two unnegligible limitations. The first one is that the Sinkhorn distance only gives an approximation of the real Wasserstein distance, the second one is the `divide by zero’ problem which often occurs during matrix scaling when setting the entropy regularization coefficient to a small value. In this paper, we introduce a new Brenier approach for calculating a more accurate Wasserstein distance between two discrete distributions, this approach successfully avoids the two limitations shown above for Sinkhorn distance and gives an alternative way for estimating distribution discrepancy. | |
| Tasks | |
| Published | 2018-01-17 |
| URL | http://arxiv.org/abs/1801.05574v1 |
| http://arxiv.org/pdf/1801.05574v1.pdf | |
| PWC | https://paperswithcode.com/paper/brenier-approach-for-optimal-transportation |
| Repo | |
| Framework | |
Graph-Based Ascent Algorithms for Function Maximization
| Title | Graph-Based Ascent Algorithms for Function Maximization |
| Authors | Muni Sreenivas Pydi, Varun Jog, Po-Ling Loh |
| Abstract | We study the problem of finding the maximum of a function defined on the nodes of a connected graph. The goal is to identify a node where the function obtains its maximum. We focus on local iterative algorithms, which traverse the nodes of the graph along a path, and the next iterate is chosen from the neighbors of the current iterate with probability distribution determined by the function values at the current iterate and its neighbors. We study two algorithms corresponding to a Metropolis-Hastings random walk with different transition kernels: (i) The first algorithm is an exponentially weighted random walk governed by a parameter $\gamma$. (ii) The second algorithm is defined with respect to the graph Laplacian and a smoothness parameter $k$. We derive convergence rates for the two algorithms in terms of total variation distance and hitting times. We also provide simulations showing the relative convergence rates of our algorithms in comparison to an unbiased random walk, as a function of the smoothness of the graph function. Our algorithms may be categorized as a new class of “descent-based” methods for function maximization on the nodes of a graph. |
| Tasks | |
| Published | 2018-02-13 |
| URL | http://arxiv.org/abs/1802.04475v1 |
| http://arxiv.org/pdf/1802.04475v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-based-ascent-algorithms-for-function |
| Repo | |
| Framework | |
MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudes
| Title | MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudes |
| Authors | Henry Gouk, Bernhard Pfahringer, Eibe Frank, Michael Cree |
| Abstract | Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as the maximum gain. We hypothesise that constraining the gain of a network will have a regularising effect, similar to how constraining the Lipschitz constant of a network has been shown to improve generalisation. A simple algorithm is provided that involves rescaling the weight matrix of each layer after each parameter update. We conduct a series of studies on common benchmark datasets, and also a novel dataset that we introduce to enable easier significance testing for experiments using convolutional networks. Performance on these datasets compares favourably with other common regularisation techniques. |
| Tasks | |
| Published | 2018-04-16 |
| URL | http://arxiv.org/abs/1804.05965v2 |
| http://arxiv.org/pdf/1804.05965v2.pdf | |
| PWC | https://paperswithcode.com/paper/maxgain-regularisation-of-neural-networks-by |
| Repo | |
| Framework | |
Arap-Tweet: A Large Multi-Dialect Twitter Corpus for Gender, Age and Language Variety Identification
| Title | Arap-Tweet: A Large Multi-Dialect Twitter Corpus for Gender, Age and Language Variety Identification |
| Authors | Wajdi Zaghouani, Anis Charfi |
| Abstract | In this paper, we present Arap-Tweet, which is a large-scale and multi-dialectal corpus of Tweets from 11 regions and 16 countries in the Arab world representing the major Arabic dialectal varieties. To build this corpus, we collected data from Twitter and we provided a team of experienced annotators with annotation guidelines that they used to annotate the corpus for age categories, gender, and dialectal variety. During the data collection effort, we based our search on distinctive keywords that are specific to the different Arabic dialects and we also validated the location using Twitter API. In this paper, we report on the corpus data collection and annotation efforts. We also present some issues that we encountered during these phases. Then, we present the results of the evaluation performed to ensure the consistency of the annotation. The provided corpus will enrich the limited set of available language resources for Arabic and will be an invaluable enabler for developing author profiling tools and NLP tools for Arabic. |
| Tasks | |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07674v1 |
| http://arxiv.org/pdf/1808.07674v1.pdf | |
| PWC | https://paperswithcode.com/paper/arap-tweet-a-large-multi-dialect-twitter |
| Repo | |
| Framework | |
