scholarly journals One-Shot Neural Architecture Search via Novelty Driven Sampling

2020 ◽  
Author(s):  
Miao Zhang ◽  
Huiqi Li ◽  
Shirui Pan ◽  
Taoping Liu ◽  
Steven Su
Keyword(s):  
Sampling Method ◽  
State Of The Art ◽  
Bilevel Optimization ◽  
Test Accuracy ◽  
New Approach ◽  
Neural Architecture ◽  
Novelty Search ◽  
Effectiveness And Efficiency ◽  
The Rich ◽  
Single Path

One-Shot Neural architecture search (NAS) has received wide attentions due to its computational efficiency. Most state-of-the-art One-Shot NAS methods use the validation accuracy based on inheriting weights from the supernet as the stepping stone to search for the best performing architecture, adopting a bilevel optimization pattern with assuming this validation accuracy approximates to the test accuracy after re-training. However, recent works have found that there is no positive correlation between the above validation accuracy and test accuracy for these One-Shot NAS methods, and this reward based sampling for supernet training also entails the rich-get-richer problem. To handle this deceptive problem, this paper presents a new approach, Efficient Novelty-driven Neural Architecture Search, to sample the most abnormal architecture to train the supernet. Specifically, a single-path supernet is adopted, and only the weights of a single architecture sampled by our novelty search are optimized in each step to reduce the memory demand greatly. Experiments demonstrate the effectiveness and efficiency of our novelty search based architecture sampling method.

scholarly journals Influence Maximization with Priority in Online Social Networks

Algorithms ◽  
2020 ◽  
Vol 13 (8) ◽  
pp. 183
Author(s):  
Canh V. Pham ◽  
Dung K. T. Ha ◽  
Quang C. Vu ◽  
Anh N. Su ◽  
Huan X. Hoang
Keyword(s):  
Social Network ◽  
Online Social Networks ◽  
Sampling Method ◽  
State Of The Art ◽  
Influence Maximization ◽  
Approximation Solution ◽  
Worst Case ◽  
New Approach ◽  
Influence Spread ◽  
Seed Collections

The Influence Maximization (IM) problem, which finds a set of k nodes (called seedset) in a social network to initiate the influence spread so that the number of influenced nodes after propagation process is maximized, is an important problem in information propagation and social network analysis. However, previous studies ignored the constraint of priority that led to inefficient seed collections. In some real situations, companies or organizations often prioritize influencing potential users during their influence diffusion campaigns. With a new approach to these existing works, we propose a new problem called Influence Maximization with Priority (IMP) which finds out a set seed of k nodes in a social network to be able to influence the largest number of nodes subject to the influence spread to a specific set of nodes U (called priority set) at least a given threshold T in this paper. We show that the problem is NP-hard under well-known IC model. To find the solution, we propose two efficient algorithms, called Integrated Greedy (IG) and Integrated Greedy Sampling (IGS) with provable theoretical guarantees. IG provides a 1−(1−1k)t-approximation solution with t is an outcome of algorithm and t≥1. The worst-case approximation ratio is obtained when t=1 and it is equal to 1/k. In addition, IGS is an efficient randomized approximation algorithm based on sampling method that provides a 1−(1−1k)t−ϵ-approximation solution with probability at least 1−δ with ϵ>0,δ∈(0,1) as input parameters of the problem. We conduct extensive experiments on various real networks to compare our IGS algorithm to the state-of-the-art algorithms in IM problem. The results indicate that our algorithm provides better solutions interns of influence on the priority sets when approximately give twice to ten times higher than threshold T while running time, memory usage and the influence spread also give considerable results compared to the others.

scholarly journals Scalable Rule Learning via Learning Representation

2018 ◽  
Author(s):  
Pouya Ghiasnezhad Omran ◽  
Kewen Wang ◽  
Zhe Wang
Keyword(s):  
Link Prediction ◽  
Sampling Method ◽  
State Of The Art ◽  
Rule Learning ◽  
Representation Learning ◽  
Data Repositories ◽  
New Approach ◽  
First Order ◽  
Learning Rules ◽  
Recent Advancement

We study the problem of learning first-order rules from large Knowledge Graphs (KGs). With recent advancement in information extraction, vast data repositories in the KG format have been obtained such as Freebase and YAGO. However, traditional techniques for rule learning are not scalable for KGs. This paper presents a new approach RLvLR to learning rules from KGs by using the technique of embedding in representation learning together with a new sampling method. Experimental results show that our system outperforms some state-of-the-art systems. Specifically, for massive KGs with hundreds of predicates and over 10M facts, RLvLR is much faster and can learn much more quality rules than major systems for rule learning in KGs such as AMIE+. We also used the RLvLR-mined rules in an inference module to carry out the link prediction task. In this task, RLvLR outperformed Neural LP, a state-of-the-art link prediction system, in both runtime and accuracy.

A new approach based on graph matching and evolutionary approach for sport scheduling problem

2020 ◽  
pp. 1-16
Author(s):  
Meriem Khelifa ◽  
Dalila Boughaci ◽  
Esma Aïmeur
Keyword(s):  
Graph Matching ◽  
State Of The Art ◽  
Travel Cost ◽  
Round Robin ◽  
New Approach ◽  
Traveling Tournament Problem ◽  
Significant Interest ◽  
National League ◽  
Better Than

The Traveling Tournament Problem (TTP) is concerned with finding a double round-robin tournament schedule that minimizes the total distances traveled by the teams. It has attracted significant interest recently since a favorable TTP schedule can result in significant savings for the league. This paper proposes an original evolutionary algorithm for TTP. We first propose a quick and effective constructive algorithm to construct a Double Round Robin Tournament (DRRT) schedule with low travel cost. We then describe an enhanced genetic algorithm with a new crossover operator to improve the travel cost of the generated schedules. A new heuristic for ordering efficiently the scheduled rounds is also proposed. The latter leads to significant enhancement in the quality of the schedules. The overall method is evaluated on publicly available standard benchmarks and compared with other techniques for TTP and UTTP (Unconstrained Traveling Tournament Problem). The computational experiment shows that the proposed approach could build very good solutions comparable to other state-of-the-art approaches or better than the current best solutions on UTTP. Further, our method provides new valuable solutions to some unsolved UTTP instances and outperforms prior methods for all US National League (NL) instances.

scholarly journals Bin2vec: learning representations of binary executable programs for security tasks

Cybersecurity ◽  
2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Shushan Arakelyan ◽  
Sima Arasteh ◽  
Christophe Hauser ◽  
Erik Kline ◽  
Aram Galstyan
Keyword(s):  
Program Analysis ◽  
State Of The Art ◽  
Classification Error ◽  
New Approach ◽  
Convolutional Networks ◽  
Computational Program ◽  
Functional Algorithm ◽  
Binary Program ◽  
Vulnerability Discovery ◽  
Executable Programs

AbstractTackling binary program analysis problems has traditionally implied manually defining rules and heuristics, a tedious and time consuming task for human analysts. In order to improve automation and scalability, we propose an alternative direction based on distributed representations of binary programs with applicability to a number of downstream tasks. We introduce Bin2vec, a new approach leveraging Graph Convolutional Networks (GCN) along with computational program graphs in order to learn a high dimensional representation of binary executable programs. We demonstrate the versatility of this approach by using our representations to solve two semantically different binary analysis tasks – functional algorithm classification and vulnerability discovery. We compare the proposed approach to our own strong baseline as well as published results, and demonstrate improvement over state-of-the-art methods for both tasks. We evaluated Bin2vec on 49191 binaries for the functional algorithm classification task, and on 30 different CWE-IDs including at least 100 CVE entries each for the vulnerability discovery task. We set a new state-of-the-art result by reducing the classification error by 40% compared to the source-code based inst2vec approach, while working on binary code. For almost every vulnerability class in our dataset, our prediction accuracy is over 80% (and over 90% in multiple classes).

scholarly journals Target Localization via Integrated and Segregated Ranging Based on RSS and TOA Measurements

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 230 ◽  
Author(s):  
Slavisa Tomic ◽  
Marko Beko
Keyword(s):  
State Of The Art ◽  
Hybrid Approach ◽  
Critical Distance ◽  
Heuristic Approach ◽  
Target Localization ◽  
Line Of Sight ◽  
Time Of Arrival ◽  
Individual Measurement ◽  
New Approach ◽  
Non Line Of Sight

This work addresses the problem of target localization in adverse non-line-of-sight (NLOS) environments by using received signal strength (RSS) and time of arrival (TOA) measurements. It is inspired by a recently published work in which authors discuss about a critical distance below and above which employing combined RSS-TOA measurements is inferior to employing RSS-only and TOA-only measurements, respectively. Here, we revise state-of-the-art estimators for the considered target localization problem and study their performance against their counterparts that employ each individual measurement exclusively. It is shown that the hybrid approach is not the best one by default. Thus, we propose a simple heuristic approach to choose the best measurement for each link, and we show that it can enhance the performance of an estimator. The new approach implicitly relies on the concept of the critical distance, but does not assume certain link parameters as given. Our simulations corroborate with findings available in the literature for line-of-sight (LOS) to a certain extent, but they indicate that more work is required for NLOS environments. Moreover, they show that the heuristic approach works well, matching or even improving the performance of the best fixed choice in all considered scenarios.

scholarly journals Evaluation of the effectiveness and efficiency of state-of-the-art features and models for automatic speech recognition error detection

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Asmaa El Hannani ◽  
Rahhal Errattahi ◽  
Fatima Zahra Salmam ◽  
Thomas Hain ◽  
Hassan Ouahmane
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Error Detection ◽  
State Of The Art ◽  
Rapid Development ◽  
Unified Framework ◽  
Human Machine Interaction ◽  
Detection Analysis ◽  
Extensive Evaluation ◽  
Effectiveness And Efficiency

AbstractSpeech based human-machine interaction and natural language understanding applications have seen a rapid development and wide adoption over the last few decades. This has led to a proliferation of studies that investigate Error detection and classification in Automatic Speech Recognition (ASR) systems. However, different data sets and evaluation protocols are used, making direct comparisons of the proposed approaches (e.g. features and models) difficult. In this paper we perform an extensive evaluation of the effectiveness and efficiency of state-of-the-art approaches in a unified framework for both errors detection and errors type classification. We make three primary contributions throughout this paper: (1) we have compared our Variant Recurrent Neural Network (V-RNN) model with three other state-of-the-art neural based models, and have shown that the V-RNN model is the most effective classifier for ASR error detection in term of accuracy and speed, (2) we have compared four features’ settings, corresponding to different categories of predictor features and have shown that the generic features are particularly suitable for real-time ASR error detection applications, and (3) we have looked at the post generalization ability of our error detection framework and performed a detailed post detection analysis in order to perceive the recognition errors that are difficult to detect.

scholarly journals Translucent Answer Predictions in Multi-Hop Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 7700-7707
Author(s):  
G P Shrivatsa Bhargav ◽  
Michael Glass ◽  
Dinesh Garg ◽  
Shirish Shevade ◽  
Saswati Dana ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Local Context ◽  
The Novel ◽  
Loose Coupling ◽  
Loosely Coupled ◽  
Neural Architecture ◽  
Coupled Networks ◽  
Novel Design

Research on the task of Reading Comprehension style Question Answering (RCQA) has gained momentum in recent years due to the emergence of human annotated datasets and associated leaderboards, for example CoQA, HotpotQA, SQuAD, TriviaQA, etc. While state-of-the-art has advanced considerably, there is still ample opportunity to advance it further on some important variants of the RCQA task. In this paper, we propose a novel deep neural architecture, called TAP (Translucent Answer Prediction), to identify answers and evidence (in the form of supporting facts) in an RCQA task requiring multi-hop reasoning. TAP comprises two loosely coupled networks – Local and Global Interaction eXtractor (LoGIX) and Answer Predictor (AP). LoGIX predicts supporting facts, whereas AP consumes these predicted supporting facts to predict the answer span. The novel design of LoGIX is inspired by two key design desiderata – local context and global interaction– that we identified by analyzing examples of multi-hop RCQA task. The loose coupling between LoGIX and the AP reveals the set of sentences used by the AP in predicting an answer. Therefore, answer predictions of TAP can be interpreted in a translucent manner. TAP offers state-of-the-art performance on the HotpotQA (Yang et al. 2018) dataset – an apt dataset for multi-hop RCQA task – as it occupies Rank-1 on its leaderboard (https://hotpotqa.github.io/) at the time of submission.

scholarly journals One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

2021 ◽  
Vol 5 (3) ◽  
pp. 1-34
Author(s):  
Bingqian Lu ◽  
Jianyi Yang ◽  
Weiwen Jiang ◽  
Yiyu Shi ◽  
Shaolei Ren
Keyword(s):  
State Of The Art ◽  
Autonomous Driving ◽  
Pareto Optimal ◽  
Video Content ◽  
Fast Evaluation ◽  
Video Content Analysis ◽  
Search Spaces ◽  
Neural Architecture ◽  
Real World Applications ◽  
Prohibitive Cost

Convolutional neural networks (CNNs) are used in numerous real-world applications such as vision-based autonomous driving and video content analysis. To run CNN inference on various target devices, hardware-aware neural architecture search (NAS) is crucial. A key requirement of efficient hardware-aware NAS is the fast evaluation of inference latencies in order to rank different architectures. While building a latency predictor for each target device has been commonly used in state of the art, this is a very time-consuming process, lacking scalability in the presence of extremely diverse devices. In this work, we address the scalability challenge by exploiting latency monotonicity --- the architecture latency rankings on different devices are often correlated. When strong latency monotonicity exists, we can re-use architectures searched for one proxy device on new target devices, without losing optimality. In the absence of strong latency monotonicity, we propose an efficient proxy adaptation technique to significantly boost the latency monotonicity. Finally, we validate our approach and conduct experiments with devices of different platforms on multiple mainstream search spaces, including MobileNet-V2, MobileNet-V3, NAS-Bench-201, ProxylessNAS and FBNet. Our results highlight that, by using just one proxy device, we can find almost the same Pareto-optimal architectures as the existing per-device NAS, while avoiding the prohibitive cost of building a latency predictor for each device.

scholarly journals TripletProt: Deep Representation Learning of Proteins based on Siamese Networks

2020 ◽  
Author(s):  
Esmaeil Nourani ◽  
Ehsaneddin Asgari ◽  
Alice C. McHardy ◽  
Mohammad R.K. Mofrad
Keyword(s):  
Functional Annotation ◽  
Cellular Localization ◽  
State Of The Art ◽  
Language Model ◽  
Representation Learning ◽  
Learning Problems ◽  
Ppi Network ◽  
New Approach ◽  
Protein Protein Interaction ◽  
Siamese Networks

AbstractWe introduce TripletProt, a new approach for protein representation learning based on the Siamese neural networks. We evaluate TripletProt comprehensively in protein functional annotation tasks including sub-cellular localization (14 categories) and gene ontology prediction (more than 2000 classes), which are both challenging multi-class multi-label classification machine learning problems. We compare the performance of TripletProt with the state-of-the-art approaches including recurrent language model-based approach (i.e., UniRep), as well as protein-protein interaction (PPI) network and sequence-based method (i.e., DeepGO). Our TripletProt showed an overall improvement of F1 score in the above mentioned comprehensive functional annotation tasks, solely relying on the PPI network. TripletProt and in general Siamese Network offer great potentials for the protein informatics tasks and can be widely applied to similar tasks.

scholarly journals Fixel-based Analysis of Diffusion MRI: Methods, Applications, Challenges and Opportunities

2020 ◽  
Author(s):  
Thijs Dhollander ◽  
Adam Clemente ◽  
Mervyn Singh ◽  
Frederique Boonstra ◽  
Oren Civier ◽  
...  
Keyword(s):  
Diffusion Mri ◽  
State Of The Art ◽  
Specific Information ◽  
Analysis Framework ◽  
Wide Range ◽  
Challenges And Opportunities ◽  
P Diffusion ◽  
Modelling Techniques ◽  
The Rich

Diffusion MRI has provided the neuroimaging community with a powerful tool to acquire in-vivo data sensitive to microstructural features of white matter, up to 3 orders of magnitude smaller than typical voxel sizes. The key to extracting such valuable information lies in complex modelling techniques, which form the link between the rich diffusion MRI data and various metrics related to the microstructural organisation. Over time, increasingly advanced techniques have been developed, up to the point where some diffusion MRI models can now provide access to properties specific to individual fibre populations in each voxel in the presence of multiple "crossing" fibre pathways. While highly valuable, such fibre-specific information poses unique challenges for typical image processing pipelines and statistical analysis. In this work, we review the "fixel-based analysis" (FBA) framework that implements bespoke solutions to this end, and has recently seen a stark increase in adoption for studies of both typical (healthy) populations as well as a wide range of clinical populations. We describe the main concepts related to fixel-based analyses, as well as the methods and specific steps involved in a state-of-the-art FBA pipeline, with a focus on providing researchers with practical advice on how to interpret results. We also include an overview of the scope of current fixel-based analysis studies (until August 2020), categorised across a broad range of neuroscientific domains, listing key design choices and summarising their main results and conclusions. Finally, we critically discuss several aspects and challenges involved with the fixel-based analysis framework, and outline some directions and future opportunities.

Sign in / Sign up

Export Citation Format

Share Document