February 1, 2020

3343 words 16 mins read

Paper Group AWR 105

Convolutional neural networks: a magic bullet for gravitational-wave detection?. Coherent Semantic Attention for Image Inpainting. FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge. Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey. Interpretable Deep Learning in Drug Discovery. …

Convolutional neural networks: a magic bullet for gravitational-wave detection?


Title	Convolutional neural networks: a magic bullet for gravitational-wave detection?
Authors	Timothy D. Gebhard, Niki Kilbertus, Ian Harry, Bernhard Schölkopf
Abstract	In the last few years, machine learning techniques, in particular convolutional neural networks, have been investigated as a method to replace or complement traditional matched filtering techniques that are used to detect the gravitational-wave signature of merging black holes. However, to date, these methods have not yet been successfully applied to the analysis of long stretches of data recorded by the Advanced LIGO and Virgo gravitational-wave observatories. In this work, we critically examine the use of convolutional neural networks as a tool to search for merging black holes. We identify the strengths and limitations of this approach, highlight some common pitfalls in translating between machine learning and gravitational-wave astronomy, and discuss the interdisciplinary challenges. In particular, we explain in detail why convolutional neural networks alone cannot be used to claim a statistically significant gravitational-wave detection. However, we demonstrate how they can still be used to rapidly flag the times of potential signals in the data for a more detailed follow-up. Our convolutional neural network architecture as well as the proposed performance metrics are better suited for this task than a standard binary classifications scheme. A detailed evaluation of our approach on Advanced LIGO data demonstrates the potential of such systems as trigger generators. Finally, we sound a note of caution by constructing adversarial examples, which showcase interesting “failure modes” of our model, where inputs with no visible resemblance to real gravitational-wave signals are identified as such by the network with high confidence.
Tasks	Gravitational Wave Detection
Published	2019-04-18
URL	https://arxiv.org/abs/1904.08693v2
PDF	https://arxiv.org/pdf/1904.08693v2.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-networks-a-magic-bullet
Repo	https://github.com/timothygebhard/ggwd
Framework	none

Coherent Semantic Attention for Image Inpainting


Title	Coherent Semantic Attention for Image Inpainting
Authors	Hongyu Liu, Bin Jiang, Yi Xiao, Chao Yang
Abstract	The latest deep learning-based approaches have shown promising results for the challenging task of inpainting missing regions of an image. However, the existing methods often generate contents with blurry textures and distorted structures due to the discontinuity of the local pixels. From a semantic-level perspective, the local pixel discontinuity is mainly because these methods ignore the semantic relevance and feature continuity of hole regions. To handle this problem, we investigate the human behavior in repairing pictures and propose a fined deep generative model-based approach with a novel coherent semantic attention (CSA) layer, which can not only preserve contextual structure but also make more effective predictions of missing parts by modeling the semantic relevance between the holes features. The task is divided into rough, refinement as two steps and model each step with a neural network under the U-Net architecture, where the CSA layer is embedded into the encoder of refinement step. To stabilize the network training process and promote the CSA layer to learn more effective parameters, we propose a consistency loss to enforce the both the CSA layer and the corresponding layer of the CSA in decoder to be close to the VGG feature layer of a ground truth image simultaneously. The experiments on CelebA, Places2, and Paris StreetView datasets have validated the effectiveness of our proposed methods in image inpainting tasks and can obtain images with a higher quality as compared with the existing state-of-the-art approaches.
Tasks	Image Inpainting
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12384v3
PDF	https://arxiv.org/pdf/1905.12384v3.pdf
PWC	https://paperswithcode.com/paper/coherent-semantic-attention-for-image
Repo	https://github.com/KumapowerLIU/CSA-inpainting
Framework	pytorch

FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge


Title	FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge
Authors	Cong Hao, Xiaofan Zhang, Yuhong Li, Sitao Huang, Jinjun Xiong, Kyle Rupnow, Wen-mei Hwu, Deming Chen
Abstract	While embedded FPGAs are attractive platforms for DNN acceleration on edge-devices due to their low latency and high energy efficiency, the scarcity of resources of edge-scale FPGA devices also makes it challenging for DNN deployment. In this paper, we propose a simultaneous FPGA/DNN co-design methodology with both bottom-up and top-down approaches: a bottom-up hardware-oriented DNN model search for high accuracy, and a top-down FPGA accelerator design considering DNN-specific characteristics. We also build an automatic co-design flow, including an Auto-DNN engine to perform hardware-oriented DNN model search, as well as an Auto-HLS engine to generate synthesizable C code of the FPGA accelerator for explored DNNs. We demonstrate our co-design approach on an object detection task using PYNQ-Z1 FPGA. Results show that our proposed DNN model and accelerator outperform the state-of-the-art FPGA designs in all aspects including Intersection-over-Union (IoU) (6.2% higher), frames per second (FPS) (2.48X higher), power consumption (40% lower), and energy efficiency (2.5X higher). Compared to GPU-based solutions, our designs deliver similar accuracy but consume far less energy.
Tasks	Object Detection
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04421v1
PDF	http://arxiv.org/pdf/1904.04421v1.pdf
PWC	https://paperswithcode.com/paper/fpgadnn-co-design-an-efficient-design
Repo	https://github.com/TomG008/SkyNet
Framework	pytorch

Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey


Title	Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
Authors	Wei Emma Zhang, Quan Z. Sheng, Ahoud Alhazmi, Chenliang Li
Abstract	With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were vulnerable to strategically modified samples, named adversarial examples. These samples are generated with some imperceptible perturbations but can fool the DNNs to give false predictions. Inspired by the popularity of generating adversarial examples for image DNNs, research efforts on attacking DNNs for textual applications emerges in recent years. However, existing perturbation methods for images cannotbe directly applied to texts as text data is discrete. In this article, we review research works that address this difference and generatetextual adversarial examples on DNNs. We collect, select, summarize, discuss and analyze these works in a comprehensive way andcover all the related information to make the article self-contained. Finally, drawing on the reviewed literature, we provide further discussions and suggestions on this topic.
Tasks
Published	2019-01-21
URL	http://arxiv.org/abs/1901.06796v3
PDF	http://arxiv.org/pdf/1901.06796v3.pdf
PWC	https://paperswithcode.com/paper/generating-textual-adversarial-examples-for
Repo	https://github.com/lihebi/biber
Framework	none

Interpretable Deep Learning in Drug Discovery


Title	Interpretable Deep Learning in Drug Discovery
Authors	Kristina Preuer, Günter Klambauer, Friedrich Rippmann, Sepp Hochreiter, Thomas Unterthiner
Abstract	Without any means of interpretation, neural networks that predict molecular properties and bioactivities are merely black boxes. We will unravel these black boxes and will demonstrate approaches to understand the learned representations which are hidden inside these models. We show how single neurons can be interpreted as classifiers which determine the presence or absence of pharmacophore- or toxicophore-like structures, thereby generating new insights and relevant knowledge for chemistry, pharmacology and biochemistry. We further discuss how these novel pharmacophores/toxicophores can be determined from the network by identifying the most relevant components of a compound for the prediction of the network. Additionally, we propose a method which can be used to extract new pharmacophores from a model and will show that these extracted structures are consistent with literature findings. We envision that having access to such interpretable knowledge is a crucial aid in the development and design of new pharmaceutically active molecules, and helps to investigate and understand failures and successes of current methods.
Tasks	Drug Discovery
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02788v2
PDF	http://arxiv.org/pdf/1903.02788v2.pdf
PWC	https://paperswithcode.com/paper/interpretable-deep-learning-in-drug-discovery
Repo	https://github.com/bioinf-jku/interpretable_ml_drug_discovery
Framework	none

Learning to Plan Hierarchically from Curriculum


Title	Learning to Plan Hierarchically from Curriculum
Authors	Philippe Morere, Lionel Ott, Fabio Ramos
Abstract	We present a framework for learning to plan hierarchically in domains with unknown dynamics. We enhance planning performance by exploiting problem structure in several ways: (i) We simplify the search over plans by leveraging knowledge of skill objectives, (ii) Shorter plans are generated by enforcing aggressively hierarchical planning, (iii) We learn transition dynamics with sparse local models for better generalisation. Our framework decomposes transition dynamics into skill effects and success conditions, which allows fast planning by reasoning on effects, while learning conditions from interactions with the world. We propose a simple method for learning new abstract skills, using successful trajectories stemming from completing the goals of a curriculum. Learned skills are then refined to leverage other abstract skills and enhance subsequent planning. We show that both conditions and abstract skills can be learned simultaneously while planning, even in stochastic domains. Our method is validated in experiments of increasing complexity, with up to 2^100 states, showing superior planning to classic non-hierarchical planners or reinforcement learning methods. Applicability to real-world problems is demonstrated in a simulation-to-real transfer experiment on a robotic manipulator.
Tasks
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07371v1
PDF	https://arxiv.org/pdf/1906.07371v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-plan-hierarchically-from
Repo	https://github.com/PhilippeMorere/learning-to-plan-hierarchically
Framework	pytorch

SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition


Title	SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition
Authors	Kaiyu Yang, Olga Russakovsky, Jia Deng
Abstract	Understanding the spatial relations between objects in images is a surprisingly challenging task. A chair may be “behind” a person even if it appears to the left of the person in the image (depending on which way the person is facing). Two students that appear close to each other in the image may not in fact be “next to” each other if there is a third student between them. We introduce SpatialSense, a dataset specializing in spatial relation recognition which captures a broad spectrum of such challenges, allowing for proper benchmarking of computer vision techniques. SpatialSense is constructed through adversarial crowdsourcing, in which human annotators are tasked with finding spatial relations that are difficult to predict using simple cues such as 2D spatial configuration or language priors. Adversarial crowdsourcing significantly reduces dataset bias and samples more interesting relations in the long tail compared to existing datasets. On SpatialSense, state-of-the-art recognition models perform comparably to simple baselines, suggesting that they rely on straightforward cues instead of fully reasoning about this complex task. The SpatialSense benchmark provides a path forward to advancing the spatial reasoning capabilities of computer vision systems. The dataset and code are available at https://github.com/princeton-vl/SpatialSense.
Tasks	Spatial Relation Recognition
Published	2019-08-07
URL	https://arxiv.org/abs/1908.02660v2
PDF	https://arxiv.org/pdf/1908.02660v2.pdf
PWC	https://paperswithcode.com/paper/spatialsense-an-adversarially-crowdsourced
Repo	https://github.com/princeton-vl/SpatialSense
Framework	pytorch

Attack Graph Obfuscation


Title	Attack Graph Obfuscation
Authors	Rami Puzis, Hadar Polad, Bracha Shapira
Abstract	Before executing an attack, adversaries usually explore the victim’s network in an attempt to infer the network topology and identify vulnerabilities in the victim’s servers and personal computers. Falsifying the information collected by the adversary post penetration may significantly slower lateral movement and increase the amount of noise generated within the victim’s network. We investigate the effect of fake vulnerabilities within a real enterprise network on the attacker performance. We use the attack graphs to model the path of an attacker making its way towards a target in a given network. We use combinatorial optimization in order to find the optimal assignments of fake vulnerabilities. We demonstrate the feasibility of our deception-based defense by presenting results of experiments with a large scale real network. We show that adding fake vulnerabilities forces the adversary to invest a significant amount of effort, in terms of time and exploitability cost.
Tasks	Combinatorial Optimization
Published	2019-03-06
URL	http://arxiv.org/abs/1903.02601v1
PDF	http://arxiv.org/pdf/1903.02601v1.pdf
PWC	https://paperswithcode.com/paper/attack-graph-obfuscation
Repo	https://github.com/impredicative/irc-rss-feed-bot
Framework	none

Differentially Private Federated Variational Inference


Title	Differentially Private Federated Variational Inference
Authors	Mrinank Sharma, Michael Hutchinson, Siddharth Swaroop, Antti Honkela, Richard E. Turner
Abstract	In many real-world applications of machine learning, data are distributed across many clients and cannot leave the devices they are stored on. Furthermore, each client’s data, computational resources and communication constraints may be very different. This setting is known as federated learning, in which privacy is a key concern. Differential privacy is commonly used to provide mathematical privacy guarantees. This work, to the best of our knowledge, is the first to consider federated, differentially private, Bayesian learning. We build on Partitioned Variational Inference (PVI) which was recently developed to support approximate Bayesian inference in the federated setting. We modify the client-side optimisation of PVI to provide an (${\epsilon}$, ${\delta}$)-DP guarantee. We show that it is possible to learn moderately private logistic regression models in the federated setting that achieve similar performance to models trained non-privately on centralised data.
Tasks	Bayesian Inference
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10563v1
PDF	https://arxiv.org/pdf/1911.10563v1.pdf
PWC	https://paperswithcode.com/paper/differentially-private-federated-variational
Repo	https://github.com/MrinankSharma/DP-PVI
Framework	pytorch

Res2Net: A New Multi-scale Backbone Architecture


Title	Res2Net: A New Multi-scale Backbone Architecture
Authors	Shang-Hua Gao, Ming-Ming Cheng, Kai Zhao, Xin-Yu Zhang, Ming-Hsuan Yang, Philip Torr
Abstract	Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.
Tasks	Image Classification, Instance Segmentation, Object Detection, Salient Object Detection
Published	2019-04-02
URL	https://arxiv.org/abs/1904.01169v2
PDF	https://arxiv.org/pdf/1904.01169v2.pdf
PWC	https://paperswithcode.com/paper/res2net-a-new-multi-scale-backbone
Repo	https://github.com/yfreedomliTHU/Res2Net
Framework	pytorch

Dating Documents using Graph Convolution Networks


Title	Dating Documents using Graph Convolution Networks
Authors	Shikhar Vashishth, Shib Sankar Dasgupta, Swayambhu Nath Ray, Partha Talukdar
Abstract	Document date is essential for many important tasks, such as document retrieval, summarization, event detection, etc. While existing approaches for these tasks assume accurate knowledge of the document date, this is not always available, especially for arbitrary documents from the Web. Document Dating is a challenging problem which requires inference over the temporal structure of the document. Prior document dating systems have largely relied on handcrafted features while ignoring such document internal structures. In this paper, we propose NeuralDater, a Graph Convolutional Network (GCN) based document dating approach which jointly exploits syntactic and temporal graph structures of document in a principled way. To the best of our knowledge, this is the first application of deep learning for the problem of document dating. Through extensive experiments on real-world datasets, we find that NeuralDater significantly outperforms state-of-the-art baseline by 19% absolute (45% relative) accuracy points.
Tasks
Published	2019-02-01
URL	http://arxiv.org/abs/1902.00175v1
PDF	http://arxiv.org/pdf/1902.00175v1.pdf
PWC	https://paperswithcode.com/paper/dating-documents-using-graph-convolution
Repo	https://github.com/malllabiisc/NeuralDater
Framework	tf

Dynamic Learning of Sequential Choice Bandit Problem under Marketing Fatigue


Title	Dynamic Learning of Sequential Choice Bandit Problem under Marketing Fatigue
Authors	Junyu Cao, Wei Sun
Abstract	Motivated by the observation that overexposure to unwanted marketing activities leads to customer dissatisfaction, we consider a setting where a platform offers a sequence of messages to its users and is penalized when users abandon the platform due to marketing fatigue. We propose a novel sequential choice model to capture multiple interactions taking place between the platform and its user: Upon receiving a message, a user decides on one of the three actions: accept the message, skip and receive the next message, or abandon the platform. Based on user feedback, the platform dynamically learns users’ abandonment distribution and their valuations of messages to determine the length of the sequence and the order of the messages, while maximizing the cumulative payoff over a horizon of length T. We refer to this online learning task as the sequential choice bandit problem. For the offline combinatorial optimization problem, we show that an efficient polynomial-time algorithm exists. For the online problem, we propose an algorithm that balances exploration and exploitation, and characterize its regret bound. Lastly, we demonstrate how to extend the model with user contexts to incorporate personalization.
Tasks	Combinatorial Optimization
Published	2019-03-19
URL	http://arxiv.org/abs/1903.08193v1
PDF	http://arxiv.org/pdf/1903.08193v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-learning-of-sequential-choice-bandit
Repo	https://github.com/bettyttytty/Thompson-Sampling-for-a-Fatigue-aware-Online-Recommendation-System
Framework	none

SoftTriple Loss: Deep Metric Learning Without Triplet Sampling


Title	SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
Authors	Qi Qian, Lei Shang, Baigui Sun, Juhua Hu, Hao Li, Rong Jin
Abstract	Distance metric learning (DML) is to learn the embeddings where examples from the same class are closer than examples from different classes. It can be cast as an optimization problem with triplet constraints. Due to the vast number of triplet constraints, a sampling strategy is essential for DML. With the tremendous success of deep learning in classifications, it has been applied for DML. When learning embeddings with deep neural networks (DNNs), only a mini-batch of data is available at each iteration. The set of triplet constraints has to be sampled within the mini-batch. Since a mini-batch cannot capture the neighbors in the original set well, it makes the learned embeddings sub-optimal. On the contrary, optimizing SoftMax loss, which is a classification loss, with DNN shows a superior performance in certain DML tasks. It inspires us to investigate the formulation of SoftMax. Our analysis shows that SoftMax loss is equivalent to a smoothed triplet loss where each class has a single center. In real-world data, one class can contain several local clusters rather than a single one, e.g., birds of different poses. Therefore, we propose the SoftTriple loss to extend the SoftMax loss with multiple centers for each class. Compared with conventional deep metric learning algorithms, optimizing SoftTriple loss can learn the embeddings without the sampling phase by mildly increasing the size of the last fully connected layer. Experiments on the benchmark fine-grained data sets demonstrate the effectiveness of the proposed loss function.
Tasks	Image Retrieval, Metric Learning
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05235v1
PDF	https://arxiv.org/pdf/1909.05235v1.pdf
PWC	https://paperswithcode.com/paper/softtriple-loss-deep-metric-learning-without
Repo	https://github.com/idstcv/SoftTriple
Framework	pytorch


Title	Blind Super-Resolution With Iterative Kernel Correction
Authors	Jinjin Gu, Hannan Lu, Wangmeng Zuo, Chao Dong
Abstract	Deep learning based methods have dominated super-resolution (SR) field due to their remarkable performance in terms of effectiveness and efficiency. Most of these methods assume that the blur kernel during downsampling is predefined/known (e.g., bicubic). However, the blur kernels involved in real applications are complicated and unknown, resulting in severe performance drop for the advanced SR methods. In this paper, we propose an Iterative Kernel Correction (IKC) method for blur kernel estimation in blind SR problem, where the blur kernels are unknown. We draw the observation that kernel mismatch could bring regular artifacts (either over-sharpening or over-smoothing), which can be applied to correct inaccurate blur kernels. Thus we introduce an iterative correction scheme – IKC that achieves better results than direct kernel estimation. We further propose an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD. Extensive experiments on synthetic and real-world images show that the proposed IKC method with SFTMD can provide visually favorable SR results and the state-of-the-art performance in blind SR problem.
Tasks	Super-Resolution
Published	2019-04-06
URL	https://arxiv.org/abs/1904.03377v2
PDF	https://arxiv.org/pdf/1904.03377v2.pdf
PWC	https://paperswithcode.com/paper/blind-super-resolution-with-iterative-kernel
Repo	https://github.com/yuanjunchai/IKC
Framework	pytorch

Comprehensive Process Drift Detection with Visual Analytics


Title	Comprehensive Process Drift Detection with Visual Analytics
Authors	Anton Yeshchenko, Claudio Di Ciccio, Jan Mendling, Artem Polyvyanyy
Abstract	Recent research has introduced ideas from concept drift into process mining to enable the analysis of changes in business processes over time. This stream of research, however, has not yet addressed the challenges of drift categorization, drilling-down, and quantification. In this paper, we propose a novel technique for managing process drifts, called Visual Drift Detection (VDD), which fulfills these requirements. The technique starts by clustering declarative process constraints discovered from recorded logs of executed business processes based on their similarity and then applies change point detection on the identified clusters to detect drifts. VDD complements these features with detailed visualizations and explanations of drifts. Our evaluation, both on synthetic and real-world logs, demonstrates all the aforementioned capabilities of the technique.
Tasks	Change Point Detection
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06386v1
PDF	https://arxiv.org/pdf/1907.06386v1.pdf
PWC	https://paperswithcode.com/paper/comprehensive-process-drift-detection-with
Repo	https://github.com/yesanton/Process-Drift-Visualization-With-Declare
Framework	none