Paper Group ANR 1443
Explainable AI for Intelligence Augmentation in Multi-Domain Operations. Nonvolatile Spintronic Memory Cells for Neural Networks. Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks. Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization. Data Generation for Neural Programming by Example. Age …
Explainable AI for Intelligence Augmentation in Multi-Domain Operations
| Title | Explainable AI for Intelligence Augmentation in Multi-Domain Operations |
| Authors | Alun Preece, Dave Braines, Federico Cerutti, Tien Pham |
| Abstract | Central to the concept of multi-domain operations (MDO) is the utilization of an intelligence, surveillance, and reconnaissance (ISR) network consisting of overlapping systems of remote and autonomous sensors, and human intelligence, distributed among multiple partners. Realising this concept requires advancement in both artificial intelligence (AI) for improved distributed data analytics and intelligence augmentation (IA) for improved human-machine cognition. The contribution of this paper is threefold: (1) we map the coalition situational understanding (CSU) concept to MDO ISR requirements, paying particular attention to the need for assured and explainable AI to allow robust human-machine decision-making where assets are distributed among multiple partners; (2) we present illustrative vignettes for AI and IA in MDO ISR, including human-machine teaming, dense urban terrain analysis, and enhanced asset interoperability; (3) we appraise the state-of-the-art in explainable AI in relation to the vignettes with a focus on human-machine collaboration to achieve more rapid and agile coalition decision-making. The union of these three elements is intended to show the potential value of a CSU approach in the context of MDO ISR, grounded in three distinct use cases, highlighting how the need for explainability in the multi-partner coalition setting is key. |
| Tasks | Decision Making |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07563v1 |
| https://arxiv.org/pdf/1910.07563v1.pdf | |
| PWC | https://paperswithcode.com/paper/explainable-ai-for-intelligence-augmentation |
| Repo | |
| Framework | |
Nonvolatile Spintronic Memory Cells for Neural Networks
| Title | Nonvolatile Spintronic Memory Cells for Neural Networks |
| Authors | Andrew W. Stephan, Qiuwen Lou, Michael Niemier, X. Sharon Hu, Steven J. Koester |
| Abstract | A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-destructive read is proposed. The cells can be used as neural computing units. A dual-circuit neural network architecture is proposed to leverage these devices against the complex operations involved in convolutional networks. Simulations based on HSPICE and Matlab were performed to study the performance of this architecture when classifying images as well as the effect of varying the size and stability of the nanomagnets. The spintronic cells outperform a purely charge-based implementation of the same network, consuming about 100 pJ total per image processed. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12679v1 |
| https://arxiv.org/pdf/1905.12679v1.pdf | |
| PWC | https://paperswithcode.com/paper/nonvolatile-spintronic-memory-cells-for |
| Repo | |
| Framework | |
Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks
| Title | Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks |
| Authors | Tribhuvanesh Orekondy, Bernt Schiele, Mario Fritz |
| Abstract | High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-world applications e.g., cloud prediction APIs. Recent advances in model functionality stealing attacks via black-box access (i.e., inputs in, predictions out) threaten the business model of such applications, which require a lot of time, money, and effort to develop. Existing defenses take a passive role against stealing attacks, such as by truncating predicted information. We find such passive defenses ineffective against DNN stealing attacks. In this paper, we propose the first defense which actively perturbs predictions targeted at poisoning the training objective of the attacker. We find our defense effective across a wide range of challenging datasets and DNN model stealing attacks, and additionally outperforms existing defenses. Our defense is the first that can withstand highly accurate model stealing attacks for tens of thousands of queries, amplifying the attacker’s error rate up to a factor of 85$\times$ with minimal impact on the utility for benign users. |
| Tasks | Autonomous Vehicles |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.10908v2 |
| https://arxiv.org/pdf/1906.10908v2.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-poisoning-utility-constrained |
| Repo | |
| Framework | |
Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
| Title | Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization |
| Authors | Pengfei Chen, Weiwen Liu, Chang-Yu Hsieh, Guangyong Chen, Shengyu Zhang |
| Abstract | Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during which parameterized transformation matrices should be learned for the node feature updating. However, existing propagation schemes are far from being optimal since they do not fully utilize the relational information between nodes. We propose the information maximizing graph neural networks (IGNN), which maximizes the mutual information between edge states and transform parameters. We reformulate the mutual information as a differentiable objective via a variational approach. We compare our model against several recent variants of GNNs and show that our model achieves the state-of-the-art performance on multiple tasks including quantum chemistry regression on QM9 dataset, generalization capability from QM9 to larger molecular graphs, and prediction of molecular bioactivities relevant for drug discovery. The IGNN model is based on an elegant and fundamental idea in information theory as explained in the main text, and it could be easily generalized beyond the contexts of molecular graphs considered in this work. To encourage more future work in this area, all datasets and codes used in this paper will be released for public access. |
| Tasks | Drug Discovery |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05488v1 |
| https://arxiv.org/pdf/1906.05488v1.pdf | |
| PWC | https://paperswithcode.com/paper/utilizing-edge-features-in-graph-neural |
| Repo | |
| Framework | |
Data Generation for Neural Programming by Example
| Title | Data Generation for Neural Programming by Example |
| Authors | Judith Clymo, Haik Manukian, Nathanaël Fijalkow, Adrià Gascón, Brooks Paige |
| Abstract | Programming by example is the problem of synthesizing a program from a small set of input / output pairs. Recent works applying machine learning methods to this task show promise, but are typically reliant on generating synthetic examples for training. A particular challenge lies in generating meaningful sets of inputs and outputs, which well-characterize a given program and accurately demonstrate its behavior. Where examples used for testing are generated by the same method as training data then the performance of a model may be partly reliant on this similarity. In this paper we introduce a novel approach using an SMT solver to synthesize inputs which cover a diverse set of behaviors for a given program. We carry out a case study comparing this method to existing synthetic data generation procedures in the literature, and find that data generated using our approach improves both the discriminatory power of example sets and the ability of trained machine learning models to generalize to unfamiliar data. |
| Tasks | Synthetic Data Generation |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02624v1 |
| https://arxiv.org/pdf/1911.02624v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-generation-for-neural-programming-by |
| Repo | |
| Framework | |
Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound
| Title | Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound |
| Authors | Haoran Dou, Xin Yang, Jikuan Qian, Wufeng Xue, Hao Qin, Xu Wang, Lequan Yu, Shujun Wang, Yi Xiong, Pheng-Ann Heng, Dong Ni |
| Abstract | Standard plane localization is crucial for ultrasound (US) diagnosis. In prenatal US, dozens of standard planes are manually acquired with a 2D probe. It is time-consuming and operator-dependent. In comparison, 3D US containing multiple standard planes in one shot has the inherent advantages of less user-dependency and more efficiency. However, manual plane localization in US volume is challenging due to the huge search space and large fetal posture variation. In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US. Our contribution is two-fold. First, we equip the RL framework with a landmark-aware alignment module to provide warm start and strong spatial bounds for the agent actions, thus ensuring its effectiveness. Second, instead of passively and empirically terminating the agent inference, we propose a recurrent neural network based strategy for active termination of the agent’s interaction procedure. This improves both the accuracy and efficiency of the localization system. Extensively validated on our in-house large dataset, our approach achieves the accuracy of 3.4mm/9.6{\deg} and 2.7mm/9.1{\deg} for the transcerebellar and transthalamic plane localization, respectively. Ourproposed RL framework is general and has the potential to improve the efficiency and standardization of US scanning. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04331v1 |
| https://arxiv.org/pdf/1910.04331v1.pdf | |
| PWC | https://paperswithcode.com/paper/agent-with-warm-start-and-active-termination |
| Repo | |
| Framework | |
Machine Learning For Distributed Acoustic Sensors, Classic versus Image and Deep Neural Networks Approach
| Title | Machine Learning For Distributed Acoustic Sensors, Classic versus Image and Deep Neural Networks Approach |
| Authors | Mugdim Bublin |
| Abstract | Distributed Acoustic Sensing (DAS) using fiber optic cables is a promising new technology for pipeline monitoring and protection. In this work, we applied and compared two approaches for event detection using DAS: Classic machine learning approach and the approach based on image processing and deep learning. Although with both approaches acceptable performance can be achieved, the preliminary results show that image based deep learning is more promising approach, offering six times lower event detection delay and twelve times lower execution time. |
| Tasks | |
| Published | 2019-04-25 |
| URL | http://arxiv.org/abs/1904.11546v1 |
| http://arxiv.org/pdf/1904.11546v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-for-distributed-acoustic |
| Repo | |
| Framework | |
Variational Autoencoders for Generative Modelling of Water Cherenkov Detectors
| Title | Variational Autoencoders for Generative Modelling of Water Cherenkov Detectors |
| Authors | Abhishek Abhishek, Wojciech Fedorko, Patrick de Perio, Nicholas Prouse, Julian Z. Ding |
| Abstract | Matter-antimatter asymmetry is one of the major unsolved problems in physics that can be probed through precision measurements of charge-parity symmetry violation at current and next-generation neutrino oscillation experiments. In this work, we demonstrate the capability of variational autoencoders and normalizing flows to approximate the generative distribution of simulated data for water Cherenkov detectors commonly used in these experiments. We study the performance of these methods and their applicability for semi-supervised learning and synthetic data generation. |
| Tasks | Synthetic Data Generation |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.02369v1 |
| https://arxiv.org/pdf/1911.02369v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-autoencoders-for-generative |
| Repo | |
| Framework | |
Answering questions by learning to rank – Learning to rank by answering questions
| Title | Answering questions by learning to rank – Learning to rank by answering questions |
| Authors | George-Sebastian Pîrtoacă, Traian Rebedea, Stefan Ruseti |
| Abstract | Answering multiple-choice questions in a setting in which no supporting documents are explicitly provided continues to stand as a core problem in natural language processing. The contribution of this article is two-fold. First, it describes a method which can be used to semantically rank documents extracted from Wikipedia or similar natural language corpora. Second, we propose a model employing the semantic ranking that holds the first place in two of the most popular leaderboards for answering multiple-choice questions: ARC Easy and Challenge. To achieve this, we introduce a self-attention based neural network that latently learns to rank documents by their importance related to a given question, whilst optimizing the objective of predicting the correct answer. These documents are considered relevant contexts for the underlying question. We have published the ranked documents so that they can be used off-the-shelf to improve downstream decision models. |
| Tasks | Learning-To-Rank |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00596v2 |
| https://arxiv.org/pdf/1909.00596v2.pdf | |
| PWC | https://paperswithcode.com/paper/answering-questions-by-learning-to-rank |
| Repo | |
| Framework | |
Directional Embedding Based Semi-supervised Framework For Bird Vocalization Segmentation
| Title | Directional Embedding Based Semi-supervised Framework For Bird Vocalization Segmentation |
| Authors | Anshul Thakur, Padmanabhan Rajan |
| Abstract | This paper proposes a data-efficient, semi-supervised, two-pass framework for segmenting bird vocalizations. The framework utilizes a binary classification model to categorize frames of an input audio recording into the background or bird vocalization. The first pass of the framework automatically generates training labels from the input recording itself, while model training and classification is done during the second pass. The proposed framework utilizes a reference directional model for obtaining a feature representation called directional embeddings (DE). This reference directional model acts as an acoustic model for bird vocalizations and is obtained using the mixtures of Von-Mises Fisher distribution (moVMF). The proposed DE space only contains information about bird vocalizations, while no information about the background disturbances is reflected. The framework employs supervised information only for obtaining the reference directional model and avoids the background modeling. Hence, it can be regarded as semi-supervised in nature. The proposed framework is tested on approximately 79000 vocalizations of seven different bird species. The performance of the framework is also analyzed in the presence of noise at different SNRs. Experimental results convey that the proposed framework performs better than the existing bird vocalization segmentation methods. |
| Tasks | |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09765v1 |
| http://arxiv.org/pdf/1902.09765v1.pdf | |
| PWC | https://paperswithcode.com/paper/directional-embedding-based-semi-supervised |
| Repo | |
| Framework | |
FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms
| Title | FastReg: Fast Non-Rigid Registration via Accelerated Optimisation on the Manifold of Diffeomorphisms |
| Authors | Daniel Grzech, Loïc le Folgoc, Mattias P. Heinrich, Bishesh Khanal, Jakub Moll, Julia A. Schnabel, Ben Glocker, Bernhard Kainz |
| Abstract | We present an implementation of a new approach to diffeomorphic non-rigid registration of medical images. The method is based on optical flow and warps images via gradient flow with the standard $L^2$ inner product. To compute the transformation, we rely on accelerated optimisation on the manifold of diffeomorphisms. We achieve regularity properties of Sobolev gradient flows, which are expensive to compute, owing to a novel method of averaging the gradients in time rather than space. We successfully register brain MRI and challenging abdominal CT scans at speeds orders of magnitude faster than previous approaches. We make our code available in a public repository: https://github.com/dgrzech/fastreg |
| Tasks | Optical Flow Estimation |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.01905v3 |
| http://arxiv.org/pdf/1903.01905v3.pdf | |
| PWC | https://paperswithcode.com/paper/fastreg-fast-non-rigid-registration-via |
| Repo | |
| Framework | |
A Learning-Based Two-Stage Spectrum Sharing Strategy with Multiple Primary Transmit Power Levels
| Title | A Learning-Based Two-Stage Spectrum Sharing Strategy with Multiple Primary Transmit Power Levels |
| Authors | Rui Zhang, Peng Cheng, Zhuo Chen, Yonghui Li, Branka Vucetic |
| Abstract | Multi-parameter cognition in a cognitive radio network (CRN) provides a more thorough understanding of the radio environments, and could potentially lead to far more intelligent and efficient spectrum usage for a secondary user. In this paper, we investigate the multi-parameter cognition problem for a CRN where the primary transmitter (PT) radiates multiple transmit power levels, and propose a learning-based two-stage spectrum sharing strategy. We first propose a data-driven/machine learning based multi-level spectrum sensing scheme, including the spectrum learning (Stage I) and prediction (the first part in Stage II). This fully blind sensing scheme does not require any prior knowledge of the PT power characteristics. Then, based on a novel normalized power level alignment metric, we propose two prediction-transmission structures, namely periodic and non-periodic, for spectrum access (the second part in Stage II), which enable the secondary transmitter (ST) to closely follow the PT power level variation. The periodic structure features a fixed prediction interval, while the non-periodic one dynamically determines the interval with a proposed reinforcement learning algorithm to further improve the alignment metric. Finally, we extend the prediction-transmission structure to an online scenario, where the number of PT power levels might change as a consequence of PT adapting to the environment fluctuation or quality of service variation. The simulation results demonstrate the effectiveness of the proposed strategy in various scenarios. |
| Tasks | |
| Published | 2019-07-21 |
| URL | https://arxiv.org/abs/1907.09949v1 |
| https://arxiv.org/pdf/1907.09949v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-learning-based-two-stage-spectrum-sharing |
| Repo | |
| Framework | |
Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks
| Title | Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks |
| Authors | Haoyang Huang, Yaobo Liang, Nan Duan, Ming Gong, Linjun Shou, Daxin Jiang, Ming Zhou |
| Abstract | We present Unicoder, a universal language encoder that is insensitive to different languages. Given an arbitrary NLP task, a model can be trained with Unicoder using training data in one language and directly applied to inputs of the same task in other languages. Comparing to similar efforts such as Multilingual BERT and XLM, three new cross-lingual pre-training tasks are proposed, including cross-lingual word recovery, cross-lingual paraphrase classification and cross-lingual masked language model. These tasks help Unicoder learn the mappings among different languages from more perspectives. We also find that doing fine-tuning on multiple languages together can bring further improvement. Experiments are performed on two tasks: cross-lingual natural language inference (XNLI) and cross-lingual question answering (XQA), where XLM is our baseline. On XNLI, 1.8% averaged accuracy improvement (on 15 languages) is obtained. On XQA, which is a new cross-lingual dataset built by us, 5.5% averaged accuracy improvement (on French and German) is obtained. |
| Tasks | Cross-Lingual Natural Language Inference, Language Modelling, Natural Language Inference, Question Answering |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.00964v2 |
| https://arxiv.org/pdf/1909.00964v2.pdf | |
| PWC | https://paperswithcode.com/paper/unicoder-a-universal-language-encoder-by-pre |
| Repo | |
| Framework | |
RefineFace: Refinement Neural Network for High Performance Face Detection
| Title | RefineFace: Refinement Neural Network for High Performance Face Detection |
| Authors | Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li |
| Abstract | Face detection has achieved significant progress in recent years. However, high performance face detection still remains a very challenging problem, especially when there exists many tiny faces. In this paper, we present a single-shot refinement face detector namely RefineFace to achieve high performance. Specifically, it consists of five modules: Selective Two-step Regression (STR), Selective Two-step Classification (STC), Scale-aware Margin Loss (SML), Feature Supervision Module (FSM) and Receptive Field Enhancement (RFE). To enhance the regression ability for high location accuracy, STR coarsely adjusts locations and sizes of anchors from high level detection layers to provide better initialization for subsequent regressor. To improve the classification ability for high recall efficiency, STC first filters out most simple negatives from low level detection layers to reduce search space for subsequent classifier, then SML is applied to better distinguish faces from background at various scales and FSM is introduced to let the backbone learn more discriminative features for classification. Besides, RFE is presented to provide more diverse receptive field to better capture faces in some extreme poses. Extensive experiments conducted on WIDER FACE, AFW, PASCAL Face, FDDB, MAFA demonstrate that our method achieves state-of-the-art results and runs at $37.3$ FPS with ResNet-18 for VGA-resolution images. |
| Tasks | Face Detection |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04376v1 |
| https://arxiv.org/pdf/1909.04376v1.pdf | |
| PWC | https://paperswithcode.com/paper/refineface-refinement-neural-network-for-high |
| Repo | |
| Framework | |
MCPA: Program Analysis as Machine Learning
| Title | MCPA: Program Analysis as Machine Learning |
| Authors | Marcel Böhme |
| Abstract | Static program analysis today takes an analytical approach which is quite suitable for a well-scoped system. Data- and control-flow is taken into account. Special cases such as pointers, procedures, and undefined behavior must be handled. A program is analyzed precisely on the statement level. However, the analytical approach is ill-equiped to handle implementations of complex, large-scale, heterogeneous software systems we see in the real world. Existing static analysis techniques that scale, trade correctness (i.e., soundness or completeness) for scalability and build on strong assumptions (e.g., language-specificity). Scalable static analysis are well-known to report errors that do not exist (false positives) or fail to report errors that do exist (false negatives). Then, how do we know the degree to which the analysis outcome is correct? In this paper, we propose an approach to scale-oblivious greybox program analysis with bounded error which applies efficient approximation schemes (FPRAS) from the foundations of machine learning: PAC learnability. Given two parameters $\delta$ and $\epsilon$, with probability at least $(1-\delta)$, our Monte Carlo Program Analysis (MCPA) approach produces an outcome that has an average error at most $\epsilon$. The parameters $\delta>0$ and $\epsilon>0$ can be chosen arbitrarily close to zero (0) such that the program analysis outcome is said to be probably-approximately correct (PAC). We demonstrate the pertinent concepts of MCPA using three applications: $(\epsilon,\delta)$-approximate quantitative analysis, $(\epsilon,\delta)$-approximate software verification, and $(\epsilon,\delta)$-approximate patch verification. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04687v1 |
| https://arxiv.org/pdf/1911.04687v1.pdf | |
| PWC | https://paperswithcode.com/paper/mcpa-program-analysis-as-machine-learning |
| Repo | |
| Framework | |
