January 31, 2020

3010 words 15 mins read

Paper Group ANR 42

Deep CNN frameworks comparison for malaria diagnosis. PIE – Proving, Interpolating and Eliminating on the Basis of First-Order Logic. Logic Rules Powered Knowledge Graph Embedding. Finding Friend and Foe in Multi-Agent Games. Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training. Multi-Stage Self-Supervise …

Deep CNN frameworks comparison for malaria diagnosis


Title	Deep CNN frameworks comparison for malaria diagnosis
Authors	Priyadarshini Adyasha Pattanaik, Zelong Wang, Patrick Horain
Abstract	We compare Deep Convolutional Neural Networks (DCNN) frameworks, namely AlexNet and VGGNet, for the classification of healthy and malaria-infected cells in large, grayscale, low quality and low resolution microscopic images, in the case only a small training set is available. Experimental results deliver promising results on the path to quick, automatic and precise classification in unstained images.
Tasks
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02829v1
PDF	https://arxiv.org/pdf/1909.02829v1.pdf
PWC	https://paperswithcode.com/paper/deep-cnn-frameworks-comparison-for-malaria
Repo
Framework

PIE – Proving, Interpolating and Eliminating on the Basis of First-Order Logic


Title	PIE – Proving, Interpolating and Eliminating on the Basis of First-Order Logic
Authors	Christoph Wernhard
Abstract	PIE is a Prolog-embedded environment for automated reasoning on the basis of first-order logic. It includes a versatile formula macro system and supports the creation of documents that intersperse macro definitions, reasoner invocations and LaTeX-formatted natural language text. Invocation of various reasoners is supported: External provers as well as sub-systems of PIE, which include preprocessors, a Prolog-based first-order prover, methods for Craig interpolation and methods for second-order quantifier elimination.
Tasks
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11137v1
PDF	https://arxiv.org/pdf/1908.11137v1.pdf
PWC	https://paperswithcode.com/paper/pie-proving-interpolating-and-eliminating-on
Repo
Framework

Logic Rules Powered Knowledge Graph Embedding


Title	Logic Rules Powered Knowledge Graph Embedding
Authors	Pengwei Wang, Dejing Dou, Fangzhao Wu, Nisansa de Silva, Lianwen Jin
Abstract	Large scale knowledge graph embedding has attracted much attention from both academia and industry in the field of Artificial Intelligence. However, most existing methods concentrate solely on fact triples contained in the given knowledge graph. Inspired by the fact that logic rules can provide a flexible and declarative language for expressing rich background knowledge, it is natural to integrate logic rules into knowledge graph embedding, to transfer human knowledge to entity and relation embedding, and strengthen the learning process. In this paper, we propose a novel logic rule-enhanced method which can be easily integrated with any translation based knowledge graph embedding model, such as TransE . We first introduce a method to automatically mine the logic rules and corresponding confidences from the triples. And then, to put both triples and mined logic rules within the same semantic space, all triples in the knowledge graph are represented as first-order logic. Finally, we define several operations on the first-order logic and minimize a global loss over both of the mined logic rules and the transformed first-order logics. We conduct extensive experiments for link prediction and triple classification on three datasets: WN18, FB166, and FB15K. Experiments show that the rule-enhanced method can significantly improve the performance of several baselines. The highlight of our model is that the filtered Hits@1, which is a pivotal evaluation in the knowledge inference task, has a significant improvement (up to 700% improvement).
Tasks	Graph Embedding, Knowledge Graph Embedding, Link Prediction
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03772v1
PDF	http://arxiv.org/pdf/1903.03772v1.pdf
PWC	https://paperswithcode.com/paper/logic-rules-powered-knowledge-graph-embedding
Repo
Framework

Finding Friend and Foe in Multi-Agent Games


Title	Finding Friend and Foe in Multi-Agent Games
Authors	Jack Serrino, Max Kleiman-Weiner, David C. Parkes, Joshua B. Tenenbaum
Abstract	Recent breakthroughs in AI for multi-agent games like Go, Poker, and Dota, have seen great strides in recent years. Yet none of these games address the real-life challenge of cooperation in the presence of unknown and uncertain teammates. This challenge is a key game mechanism in hidden role games. Here we develop the DeepRole algorithm, a multi-agent reinforcement learning agent that we test on The Resistance: Avalon, the most popular hidden role game. DeepRole combines counterfactual regret minimization (CFR) with deep value networks trained through self-play. Our algorithm integrates deductive reasoning into vector-form CFR to reason about joint beliefs and deduce partially observable actions. We augment deep value networks with constraints that yield interpretable representations of win probabilities. These innovations enable DeepRole to scale to the full Avalon game. Empirical game-theoretic methods show that DeepRole outperforms other hand-crafted and learned agents in five-player Avalon. DeepRole played with and against human players on the web in hybrid human-agent teams. We find that DeepRole outperforms human players as both a cooperator and a competitor.
Tasks	Multi-agent Reinforcement Learning
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02330v1
PDF	https://arxiv.org/pdf/1906.02330v1.pdf
PWC	https://paperswithcode.com/paper/finding-friend-and-foe-in-multi-agent-games
Repo
Framework

Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training


Title	Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training
Authors	Harrison Nguyen, Simon Luo, Fabio Ramos
Abstract	Magnetic Resonance Imaging (MRI) of the brain can come in the form of different modalities such as T1-weighted and Fluid Attenuated Inversion Recovery (FLAIR) which has been used to investigate a wide range of neurological disorders. Current state-of-the-art models for brain tissue segmentation and disease classification require multiple modalities for training and inference. However, the acquisition of all of these modalities are expensive, time-consuming, inconvenient and the required modalities are often not available. As a result, these datasets contain large amounts of \emph{unpaired} data, where examples in the dataset do not contain all modalities. On the other hand, there is smaller fraction of examples that contain all modalities (\emph{paired} data) and furthermore each modality is high dimensional when compared to number of datapoints. In this work, we develop a method to address these issues with semi-supervised learning in translating between two neuroimaging modalities. Our proposed model, Semi-Supervised Adversarial CycleGAN (SSA-CGAN), uses an adversarial loss to learn from \emph{unpaired} data points, cycle loss to enforce consistent reconstructions of the mappings and another adversarial loss to take advantage of \emph{paired} data points. Our experiments demonstrate that our proposed framework produces an improvement in reconstruction error and reduced variance for the pairwise translation of multiple modalities and is more robust to thermal noise when compared to existing methods.
Tasks
Published	2019-12-09
URL	https://arxiv.org/abs/1912.04391v1
PDF	https://arxiv.org/pdf/1912.04391v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-approach-to-generate
Repo
Framework

Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels


Title	Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels
Authors	Ke Sun, Zhouchen Lin, Zhanxing Zhu
Abstract	Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting in M3S Training Algorithm. Finally, extensive experimental results verify the superior performance of our algorithm on graphs with few labeled nodes under different label rates compared with other state-of-the-art approaches.
Tasks	Graph Embedding
Published	2019-02-28
URL	https://arxiv.org/abs/1902.11038v2
PDF	https://arxiv.org/pdf/1902.11038v2.pdf
PWC	https://paperswithcode.com/paper/multi-stage-self-supervised-learning-for
Repo
Framework

Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference


Title	Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference
Authors	Xianfeng Tang, Boqing Gong, Yanwei Yu, Huaxiu Yao, Yandong Li, Haiyong Xie, Xiaoyu Wang
Abstract	Real-time traffic volume inference is key to an intelligent city. It is a challenging task because accurate traffic volumes on the roads can only be measured at certain locations where sensors are installed. Moreover, the traffic evolves over time due to the influences of weather, events, holidays, etc. Existing solutions to the traffic volume inference problem often rely on dense GPS trajectories, which inevitably fail to account for the vehicles which carry no GPS devices or have them turned off. Consequently, the results are biased to taxicabs because they are almost always online for GPS tracking. In this paper, we propose a novel framework for the citywide traffic volume inference using both dense GPS trajectories and incomplete trajectories captured by camera surveillance systems. Our approach employs a high-fidelity traffic simulator and deep reinforcement learning to recover full vehicle movements from the incomplete trajectories. In order to jointly model the recovered trajectories and dense GPS trajectories, we construct spatiotemporal graphs and use multi-view graph embedding to encode the multi-hop correlations between road segments into real-valued vectors. Finally, we infer the citywide traffic volumes by propagating the traffic values of monitored road segments to the unmonitored ones through masked pairwise similarities. Extensive experiments with two big regions in a provincial capital city in China verify the effectiveness of our approach.
Tasks	Graph Embedding
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09255v1
PDF	http://arxiv.org/pdf/1902.09255v1.pdf
PWC	https://paperswithcode.com/paper/joint-modeling-of-dense-and-incomplete
Repo
Framework

Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling


Title	Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
Authors	Hao Wang, Chengzhi Mao, Hao He, Mingmin Zhao, Tommi S. Jaakkola, Dina Katabi
Abstract	We consider the problem of inferring the values of an arbitrary set of variables (e.g., risk of diseases) given other observed variables (e.g., symptoms and diagnosed diseases) and high-dimensional signals (e.g., MRI images or EEG). This is a common problem in healthcare since variables of interest often differ for different patients. Existing methods including Bayesian networks and structured prediction either do not incorporate high-dimensional signals or fail to model conditional dependencies among variables. To address these issues, we propose bidirectional inference networks (BIN), which stich together multiple probabilistic neural networks, each modeling a conditional dependency. Predictions are then made via iteratively updating variables using backpropagation (BP) to maximize corresponding posterior probability. Furthermore, we extend BIN to composite BIN (CBIN), which involves the iterative prediction process in the training stage and improves both accuracy and computational efficiency by adaptively smoothing the optimization landscape. Experiments on synthetic and real-world datasets (a sleep study and a dermatology dataset) show that CBIN is a single model that can achieve state-of-the-art performance and obtain better accuracy in most inference tasks than multiple models each specifically trained for a different task.
Tasks	EEG, Sleep Quality, Structured Prediction
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02037v1
PDF	http://arxiv.org/pdf/1902.02037v1.pdf
PWC	https://paperswithcode.com/paper/bidirectional-inference-networks-a-class-of
Repo
Framework

Robust Graph Embedding with Noisy Link Weights


Title	Robust Graph Embedding with Noisy Link Weights
Authors	Akifumi Okuno, Hidetoshi Shimodaira
Abstract	We propose $\beta$-graph embedding for robustly learning feature vectors from data vectors and noisy link weights. A newly introduced empirical moment $\beta$-score reduces the influence of contamination and robustly measures the difference between the underlying correct expected weights of links and the specified generative model. The proposed method is computationally tractable; we employ a minibatch-based efficient stochastic algorithm and prove that this algorithm locally minimizes the empirical moment $\beta$-score. We conduct numerical experiments on synthetic and real-world datasets.
Tasks	Graph Embedding
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08440v1
PDF	http://arxiv.org/pdf/1902.08440v1.pdf
PWC	https://paperswithcode.com/paper/robust-graph-embedding-with-noisy-link
Repo
Framework

Variational Quantum Circuit Model for Knowledge Graphs Embedding


Title	Variational Quantum Circuit Model for Knowledge Graphs Embedding
Authors	Yunpu Ma, Volker Tresp, Liming Zhao, Yuyi Wang
Abstract	In this work, we propose the first quantum Ans"atze for the statistical relational learning on knowledge graphs using parametric quantum circuits. We introduce two types of variational quantum circuits for knowledge graph embedding. Inspired by the classical representation learning, we first consider latent features for entities as coefficients of quantum states, while predicates are characterized by parametric gates acting on the quantum states. For the first model, the quantum advantages disappear when it comes to the optimization of this model. Therefore, we introduce a second quantum circuit model where embeddings of entities are generated from parameterized quantum gates acting on the pure quantum state. The benefit of the second method is that the quantum embeddings can be trained efficiently meanwhile preserving the quantum advantages. We show the proposed methods can achieve comparable results to the state-of-the-art classical models, e.g., RESCAL, DistMult. Furthermore, after optimizing the models, the complexity of inductive inference on the knowledge graphs might be reduced with respect to the number of entities.
Tasks	Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs, Relational Reasoning, Representation Learning
Published	2019-02-19
URL	http://arxiv.org/abs/1903.00556v1
PDF	http://arxiv.org/pdf/1903.00556v1.pdf
PWC	https://paperswithcode.com/paper/variational-quantum-circuit-model-for
Repo
Framework

GENO – GENeric Optimization for Classical Machine Learning


Title	GENO – GENeric Optimization for Classical Machine Learning
Authors	Sören Laue, Matthias Mitterreiter, Joachim Giesen
Abstract	Although optimization is the longstanding algorithmic backbone of machine learning, new models still require the time-consuming implementation of new solvers. As a result, there are thousands of implementations of optimization algorithms for machine learning problems. A natural question is, if it is always necessary to implement a new solver, or if there is one algorithm that is sufficient for most models. Common belief suggests that such a one-algorithm-fits-all approach cannot work, because this algorithm cannot exploit model specific structure and thus cannot be efficient and robust on a wide variety of problems. Here, we challenge this common belief. We have designed and implemented the optimization framework GENO (GENeric Optimization) that combines a modeling language with a generic solver. GENO generates a solver from the declarative specification of an optimization problem class. The framework is flexible enough to encompass most of the classical machine learning problems. We show on a wide variety of classical but also some recently suggested problems that the automatically generated solvers are (1) as efficient as well-engineered specialized solvers, (2) more efficient by a decent margin than recent state-of-the-art solvers, and (3) orders of magnitude more efficient than classical modeling language plus solver approaches.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1905.13587v1
PDF	https://arxiv.org/pdf/1905.13587v1.pdf
PWC	https://paperswithcode.com/paper/geno-generic-optimization-for-classical
Repo
Framework

Mitigating Metaphors: A Comprehensible Guide to Recent Nature-Inspired Algorithms


Title	Mitigating Metaphors: A Comprehensible Guide to Recent Nature-Inspired Algorithms
Authors	Michael Adam Lones
Abstract	In recent years, a plethora of new metaheuristic algorithms have explored different sources of inspiration within the biological and natural worlds. This nature-inspired approach to algorithm design has been widely criticised. A notable issue is the tendency for authors to use terminology that is derived from the domain of inspiration, rather than the broader domains of metaheuristics and optimisation. This makes it difficult to both comprehend how these algorithms work and understand their relationships to other metaheuristics. This paper attempts to address this issue, at least to some extent, by providing accessible descriptions of the most cited nature-inspired algorithms published in the last twenty years. It also discusses commonalities between these algorithms and more classical nature-inspired metaheuristics such as evolutionary algorithms and particle swarm optimisation, and finishes with a discussion of future directions for the field.
Tasks
Published	2019-02-21
URL	https://arxiv.org/abs/1902.08001v2
PDF	https://arxiv.org/pdf/1902.08001v2.pdf
PWC	https://paperswithcode.com/paper/mitigating-metaphors-a-comprehensible-guide
Repo
Framework

Automatic Compiler Based FPGA Accelerator for CNN Training


Title	Automatic Compiler Based FPGA Accelerator for CNN Training
Authors	Shreyas Kolala Venkataramanaiah, Yufei Ma, Shihui Yin, Eriko Nurvithadhi, Aravind Dasu, Yu Cao, Jae-sun Seo
Abstract	Training of convolutional neural networks (CNNs)on embedded platforms to support on-device learning is earning vital importance in recent days. Designing flexible training hard-ware is much more challenging than inference hardware, due to design complexity and large computation/memory requirement. In this work, we present an automatic compiler-based FPGA accelerator with 16-bit fixed-point precision for complete CNNtraining, including Forward Pass (FP), Backward Pass (BP) and Weight Update (WU). We implemented an optimized RTL library to perform training-specific tasks and developed an RTL compiler to automatically generate FPGA-synthesizable RTL based on user-defined constraints. We present a new cyclic weight storage/access scheme for on-chip BRAM and off-chip DRAMto efficiently implement non-transpose and transpose operations during FP and BP phases, respectively. Representative CNNs for CIFAR-10 dataset are implemented and trained on Intel Stratix 10-GX FPGA using proposed hardware architecture, demonstrating up to 479 GOPS performance.
Tasks
Published	2019-08-15
URL	https://arxiv.org/abs/1908.06724v1
PDF	https://arxiv.org/pdf/1908.06724v1.pdf
PWC	https://paperswithcode.com/paper/automatic-compiler-based-fpga-accelerator-for
Repo
Framework

SolarNet: A Deep Learning Framework to Map Solar Power Plants In China From Satellite Imagery


Title	SolarNet: A Deep Learning Framework to Map Solar Power Plants In China From Satellite Imagery
Authors	Xin Hou, Biao Wang, Wanqi Hu, Lei Yin, Haishan Wu
Abstract	Renewable energy such as solar power is critical to fight the ever more serious climate change. China is the world leading installer of solar panel and numerous solar power plants were built. In this paper, we proposed a deep learning framework named SolarNet which is designed to perform semantic segmentation on large scale satellite imagery data to detect solar farms. SolarNet has successfully mapped 439 solar farms in China, covering near 2000 square kilometers, equivalent to the size of whole Shenzhen city or two and a half of New York city. To the best of our knowledge, it is the first time that we used deep learning to reveal the locations and sizes of solar farms in China, which could provide insights for solar power companies, market analysts and the government.
Tasks	Semantic Segmentation
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03685v2
PDF	https://arxiv.org/pdf/1912.03685v2.pdf
PWC	https://paperswithcode.com/paper/solarnet-a-deep-learning-framework-to-map
Repo
Framework

Robotic Hierarchical Graph Neurons. A novel implementation of HGN for swarm robotic behaviour control


Title	Robotic Hierarchical Graph Neurons. A novel implementation of HGN for swarm robotic behaviour control
Authors	Phillip Smith, Aldeida Aleti, Vincent C. S. Lee, Robert Hunjet, Asad Khan
Abstract	This paper explores the use of a novel form of Hierarchical Graph Neurons (HGN) for in-operation behaviour selection in a swarm of robotic agents. This new HGN is called Robotic-HGN (R-HGN), as it matches robot environment observations to environment labels via fusion of match probabilities from both temporal and intra-swarm collections. This approach is novel for HGN as it addresses robotic observations being pseudo-continuous numbers, rather than categorical values. Additionally, the proposed approach is memory and computation-power conservative and thus is acceptable for use in mobile devices such as single-board computers, which are often used in mobile robotic agents. This R-HGN approach is validated against individual behaviour implementation and random behaviour selection. This contrast is made in two sets of simulated environments: environments designed to challenge the held behaviours of the R-HGN, and randomly generated environments which are more challenging for the robotic swarm than R-HGN training conditions. R-HGN has been found to enable appropriate behaviour selection in both these sets, allowing significant swarm performance in pre-trained and unexpected environment conditions.
Tasks
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12415v1
PDF	https://arxiv.org/pdf/1910.12415v1.pdf
PWC	https://paperswithcode.com/paper/robotic-hierarchical-graph-neurons-a-novel
Repo
Framework