Paper Group ANR 596
Learning-Based Video Game Development in MLP@UoM: An Overview. Deep learning-based prediction of kinetic parameters from myocardial perfusion MRI. Quantum-Assisted Genetic Algorithm. Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces. CoKE: Contextualized Knowledge Graph Embedding. DEGAS: Differentiable …
Learning-Based Video Game Development in MLP@UoM: An Overview
| Title | Learning-Based Video Game Development in MLP@UoM: An Overview |
| Authors | Ke Chen |
| Abstract | In general, video games not only prevail in entertainment but also have become an alternative methodology for knowledge learning, skill acquisition and assistance for medical treatment as well as health care in education, vocational/military training and medicine. On the other hand, video games also provide an ideal test bed for AI researches. To a large extent, however, video game development is still a laborious yet costly process, and there are many technical challenges ranging from game generation to intelligent agent creation. Unlike traditional methodologies, in Machine Learning and Perception Lab at the University of Manchester (MLP@UoM), we advocate applying machine learning to different tasks in video game development to address several challenges systematically. In this paper, we overview the main progress made in MLP@UoM recently and have an outlook on the future research directions in learning-based video game development arising from our works. |
| Tasks | |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10127v1 |
| https://arxiv.org/pdf/1908.10127v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-based-video-game-development-in |
| Repo | |
| Framework | |
Deep learning-based prediction of kinetic parameters from myocardial perfusion MRI
| Title | Deep learning-based prediction of kinetic parameters from myocardial perfusion MRI |
| Authors | Cian M. Scannell, Piet van den Bosch, Amedeo Chiribiri, Jack Lee, Marcel Breeuwer, Mitko Veta |
| Abstract | The quantification of myocardial perfusion MRI has the potential to provide a fast, automated and user-independent assessment of myocardial ischaemia. However, due to the relatively high noise level and low temporal resolution of the acquired data and the complexity of the tracer-kinetic models, the model fitting can yield unreliable parameter estimates. A solution to this problem is the use of Bayesian inference which can incorporate prior knowledge and improve the reliability of the parameter estimation. This, however, uses Markov chain Monte Carlo sampling to approximate the posterior distribution of the kinetic parameters which is extremely time intensive. This work proposes training convolutional networks to directly predict the kinetic parameters from the signal-intensity curves that are trained using estimates obtained from the Bayesian inference. This allows fast estimation of the kinetic parameters with a similar performance to the Bayesian inference. |
| Tasks | Bayesian Inference |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11899v1 |
| https://arxiv.org/pdf/1907.11899v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-prediction-of-kinetic |
| Repo | |
| Framework | |
Quantum-Assisted Genetic Algorithm
| Title | Quantum-Assisted Genetic Algorithm |
| Authors | James King, Masoud Mohseni, William Bernoudy, Alexandre Fréchette, Hossein Sadeghi, Sergei V. Isakov, Hartmut Neven, Mohammad H. Amin |
| Abstract | Genetic algorithms, which mimic evolutionary processes to solve optimization problems, can be enhanced by using powerful semi-local search algorithms as mutation operators. Here, we introduce reverse quantum annealing, a class of quantum evolutions that can be used for performing families of quasi-local or quasi-nonlocal search starting from a classical state, as novel sources of mutations. Reverse annealing enables the development of genetic algorithms that use quantum fluctuation for mutations and classical mechanisms for the crossovers – we refer to these as Quantum-Assisted Genetic Algorithms (QAGAs). We describe a QAGA and present experimental results using a D-Wave 2000Q quantum annealing processor. On a set of spin-glass inputs, standard (forward) quantum annealing finds good solutions very quickly but struggles to find global optima. In contrast, our QAGA proves effective at finding global optima for these inputs. This successful interplay of non-local classical and quantum fluctuations could provide a promising step toward practical applications of Noisy Intermediate-Scale Quantum (NISQ) devices for heuristic discrete optimization. |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1907.00707v1 |
| https://arxiv.org/pdf/1907.00707v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-assisted-genetic-algorithm |
| Repo | |
| Framework | |
Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces
| Title | Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces |
| Authors | Yu Qi, Bin Liu, Yueming Wang, Gang Pan |
| Abstract | Brain-computer interfaces (BCIs) have enabled prosthetic device control by decoding motor movements from neural activities. Neural signals recorded from cortex exhibit nonstationary property due to abrupt noises and neuroplastic changes in brain activities during motor control. Current state-of-the-art neural signal decoders such as Kalman filter assume fixed relationship between neural activities and motor movements, thus will fail if this assumption is not satisfied. We propose a dynamic ensemble modeling (DyEnsemble) approach that is capable of adapting to changes in neural signals by employing a proper combination of decoding functions. The DyEnsemble method firstly learns a set of diverse candidate models. Then, it dynamically selects and combines these models online according to Bayesian updating mechanism. Our method can mitigate the effect of noises and cope with different task behaviors by automatic model switching, thus gives more accurate predictions. Experiments with neural data demonstrate that the DyEnsemble method outperforms Kalman filters remarkably, and its advantage is more obvious with noisy signals. |
| Tasks | |
| Published | 2019-11-02 |
| URL | https://arxiv.org/abs/1911.00714v1 |
| https://arxiv.org/pdf/1911.00714v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-ensemble-modeling-approach-to |
| Repo | |
| Framework | |
CoKE: Contextualized Knowledge Graph Embedding
| Title | CoKE: Contextualized Knowledge Graph Embedding |
| Authors | Quan Wang, Pingping Huang, Haifeng Wang, Songtai Dai, Wenbin Jiang, Jing Liu, Yajuan Lyu, Yong Zhu, Hua Wu |
| Abstract | Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, ignoring their intrinsic contextual nature, i.e., entities and relations may appear in different graph contexts, and accordingly, exhibit different properties. This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings. Two types of graph contexts are studied: edges and paths, both formulated as sequences of entities and relations. CoKE takes a sequence as input and uses a Transformer encoder to obtain contextualized representations. These representations are hence naturally adaptive to the input, capturing contextual meanings of entities and relations therein. Evaluation on a wide variety of public benchmarks verifies the superiority of CoKE in link prediction and path query answering. It performs consistently better than, or at least equally well as current state-of-the-art in almost every case, in particular offering an absolute improvement of 19.7% in H@10 on path query answering. Our code is available at \url{https://github.com/paddlepaddle/models/tree/develop/PaddleKG/CoKE}. |
| Tasks | Graph Embedding, Knowledge Graph Embedding, Link Prediction |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02168v1 |
| https://arxiv.org/pdf/1911.02168v1.pdf | |
| PWC | https://paperswithcode.com/paper/coke-contextualized-knowledge-graph-embedding |
| Repo | |
| Framework | |
DEGAS: Differentiable Efficient Generator Search
| Title | DEGAS: Differentiable Efficient Generator Search |
| Authors | Sivan Doveh, Raja Giryes |
| Abstract | Network architecture search (NAS) achieves state-of-the-art results in various tasks such as classification and semantic segmentation. Recently, a reinforcement learning-based approach has been proposed for Generative Adversarial Networks (GANs) search. In this work, we propose an alternative strategy for GAN search by using a method called DEGAS (Differentiable Efficient GenerAtor Search), which focuses on efficiently finding the generator in the GAN. Our search algorithm is inspired by the differential architecture search strategy and the Global Latent Optimization (GLO) procedure. This leads to both an efficient and stable GAN search. After the generator architecture is found, it can be plugged into any existing framework for GAN training. For CTGAN, which we use in this work, the new model outperforms the original inception score results by 0.25 for CIFAR-10 and 0.77 for STL. It also gets better results than the RL based GAN search methods in shorter search time. |
| Tasks | Semantic Segmentation |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00606v2 |
| https://arxiv.org/pdf/1912.00606v2.pdf | |
| PWC | https://paperswithcode.com/paper/degas-differentiable-efficient-generator |
| Repo | |
| Framework | |
End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information
| Title | End-to-End Learning of Geometrical Shaping Maximizing Generalized Mutual Information |
| Authors | Kadir Gümüs, Alex Alvarado, Bin Chen, Christian Häger, Erik Agrell |
| Abstract | GMI-based end-to-end learning is shown to be highly nonconvex. We apply gradient descent initialized with Gray-labeled APSK constellations directly to the constellation coordinates. State-of-the-art constellations in 2D and 4D are found providing reach increases up to 26% w.r.t. to QAM. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05638v1 |
| https://arxiv.org/pdf/1912.05638v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-learning-of-geometrical-shaping |
| Repo | |
| Framework | |
Using Latent Codes for Class Imbalance Problem in Unsupervised Domain Adaptation
| Title | Using Latent Codes for Class Imbalance Problem in Unsupervised Domain Adaptation |
| Authors | Boris Chidlovskii |
| Abstract | We address the problem of severe class imbalance in unsupervised domain adaptation, when the class spaces in source and target domains diverge considerably. Till recently, domain adaptation methods assumed the aligned class spaces, such that reducing distribution divergence makes the transfer between domains easier. Such an alignment assumption is invalidated in real world scenarios where some source classes are often under-represented or simply absent in the target domain. We revise the current approaches to class imbalance and propose a new one that uses latent codes in the adversarial domain adaptation framework. We show how the latent codes can be used to disentangle the silent structure of the target domain and to identify under-represented classes. We show how to learn the latent code reconstruction jointly with the domain invariant representation and use them to accurately estimate the target labels. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.08962v1 |
| https://arxiv.org/pdf/1909.08962v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-latent-codes-for-class-imbalance |
| Repo | |
| Framework | |
Heterogeneous Graph Matching Networks
| Title | Heterogeneous Graph Matching Networks |
| Authors | Shen Wang, Zhengzhang Chen, Xiao Yu, Ding Li, Jingchao Ni, Lu-An Tang, Jiaping Gui, Zhichun Li, Haifeng Chen, Philip S. Yu |
| Abstract | Information systems have widely been the target of malware attacks. Traditional signature-based malicious program detection algorithms can only detect known malware and are prone to evasion techniques such as binary obfuscation, while behavior-based approaches highly rely on the malware training samples and incur prohibitively high training cost. To address the limitations of existing techniques, we propose MatchGNet, a heterogeneous Graph Matching Network model to learn the graph representation and similarity metric simultaneously based on the invariant graph modeling of the program’s execution behaviors. We conduct a systematic evaluation of our model and show that it is accurate in detecting malicious program behavior and can help detect malware attacks with less false positives. MatchGNet outperforms the state-of-the-art algorithms in malware detection by generating 50% less false positives while keeping zero false negatives. |
| Tasks | Graph Matching, Malware Detection |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.08074v1 |
| https://arxiv.org/pdf/1910.08074v1.pdf | |
| PWC | https://paperswithcode.com/paper/heterogeneous-graph-matching-networks |
| Repo | |
| Framework | |
Char-RNN and Active Learning for Hashtag Segmentation
| Title | Char-RNN and Active Learning for Hashtag Segmentation |
| Authors | Taisiya Glushkova, Ekaterina Artemova |
| Abstract | We explore the abilities of character recurrent neural network (char-RNN) for hashtag segmentation. Our approach to the task is the following: we generate synthetic training dataset according to frequent n-grams that satisfy predefined morpho-syntactic patterns to avoid any manual annotation. The active learning strategy limits the training dataset and selects informative training subset. The approach does not require any language-specific settings and is compared for two languages, which differ in inflection degree. |
| Tasks | Active Learning |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03270v1 |
| https://arxiv.org/pdf/1911.03270v1.pdf | |
| PWC | https://paperswithcode.com/paper/char-rnn-and-active-learning-for-hashtag |
| Repo | |
| Framework | |
Automated Fact Checking in the News Room
| Title | Automated Fact Checking in the News Room |
| Authors | Sebastião Miranda, David Nogueira, Afonso Mendes, Andreas Vlachos, Andrew Secker, Rebecca Garrett, Jeff Mitchel, Zita Marinho |
| Abstract | Fact checking is an essential task in journalism; its importance has been highlighted due to recently increased concerns and efforts in combating misinformation. In this paper, we present an automated fact-checking platform which given a claim, it retrieves relevant textual evidence from a document collection, predicts whether each piece of evidence supports or refutes the claim, and returns a final verdict. We describe the architecture of the system and the user interface, focusing on the choices made to improve its user-friendliness and transparency. We conduct a user study of the fact-checking platform in a journalistic setting: we integrated it with a collection of news articles and provide an evaluation of the platform using feedback from journalists in their workflow. We found that the predictions of our platform were correct 58% of the time, and 59% of the returned evidence was relevant. |
| Tasks | |
| Published | 2019-04-03 |
| URL | http://arxiv.org/abs/1904.02037v1 |
| http://arxiv.org/pdf/1904.02037v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-fact-checking-in-the-news-room |
| Repo | |
| Framework | |
Commonsense Knowledge + BERT for Level 2 Reading Comprehension Ability Test
| Title | Commonsense Knowledge + BERT for Level 2 Reading Comprehension Ability Test |
| Authors | Yidan Hu, Gongqi Lin, Yuan Miao, Chunyan Miao |
| Abstract | Commonsense knowledge plays an important role when we read. The performance of BERT on SQuAD dataset shows that the accuracy of BERT can be better than human users. However, it does not mean that computers can surpass the human being in reading comprehension. CommonsenseQA is a large-scale dataset which is designed based on commonsense knowledge. BERT only achieved an accuracy of 55.9% on it. The result shows that computers cannot apply commonsense knowledge like human beings to answer questions. Comprehension Ability Test (CAT) divided the reading comprehension ability at four levels. We can achieve human like comprehension ability level by level. BERT has performed well at level 1 which does not require common knowledge. In this research, we propose a system which aims to allow computers to read articles and answer related questions with commonsense knowledge like a human being for CAT level 2. This system consists of three parts. Firstly, we built a commonsense knowledge graph; and then automatically constructed the commonsense knowledge question dataset according to it. Finally, BERT is combined with the commonsense knowledge to achieve the reading comprehension ability at CAT level 2. Experiments show that it can pass the CAT as long as the required common knowledge is included in the knowledge base. |
| Tasks | Reading Comprehension |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03415v1 |
| https://arxiv.org/pdf/1909.03415v1.pdf | |
| PWC | https://paperswithcode.com/paper/commonsense-knowledge-bert-for-level-2 |
| Repo | |
| Framework | |
Modeling Time to Open of Emails with a Latent State for User Engagement Level
| Title | Modeling Time to Open of Emails with a Latent State for User Engagement Level |
| Authors | Moumita Sinha, Vishwa Vinay, Harvineet Singh |
| Abstract | Email messages have been an important mode of communication, not only for work, but also for social interactions and marketing. When messages have time sensitive information, it becomes relevant for the sender to know what is the expected time within which the email will be read by the recipient. In this paper we use a survival analysis framework to predict the time to open an email once it has been received. We use the Cox Proportional Hazards (CoxPH) model that offers a way to combine various features that might affect the event of opening an email. As an extension, we also apply a mixture model (MM) approach to CoxPH that distinguishes between recipients, based on a latent state of how prone to opening the messages each individual is. We compare our approach with standard classification and regression models. While the classification model provides predictions on the likelihood of an email being opened, the regression model provides prediction of the real-valued time to open. The use of survival analysis based methods allows us to jointly model both the open event as well as the time-to-open. We experimented on a large real-world dataset of marketing emails sent in a 3-month time duration. The mixture model achieves the best accuracy on our data where a high proportion of email messages go unopened. |
| Tasks | Survival Analysis |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06512v1 |
| https://arxiv.org/pdf/1908.06512v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-time-to-open-of-emails-with-a-latent |
| Repo | |
| Framework | |
Password-conditioned Anonymization and Deanonymization with Face Identity Transformers
| Title | Password-conditioned Anonymization and Deanonymization with Face Identity Transformers |
| Authors | Xiuye Gu, Weixin Luo, Michael S. Ryoo, Yong Jae Lee |
| Abstract | Cameras are prevalent in our daily lives, and enable many useful systems built upon computer vision technologies such as smart cameras and home robots for service applications. However, there is also an increasing societal concern as the captured images/videos may contain privacy-sensitive information (e.g., face identity). We propose a novel face identity transformer which enables automated photo-realistic password-based anonymization as well as deanonymization of human faces appearing in visual data. Our face identity transformer is trained to (1) remove face identity information after anonymization, (2) make the recovery of the original face possible when given the correct password, and (3) return a wrong–but photo-realistic–face given a wrong password. Extensive experiments show that our approach enables multimodal password-conditioned face anonymizations and deanonymizations, without sacrificing privacy compared to existing anonymization approaches. |
| Tasks | |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11759v2 |
| https://arxiv.org/pdf/1911.11759v2.pdf | |
| PWC | https://paperswithcode.com/paper/password-conditioned-anonymization-and |
| Repo | |
| Framework | |
VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning
| Title | VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning |
| Authors | Xiaofeng Gao, Ran Gong, Tianmin Shu, Xu Xie, Shu Wang, Song-Chun Zhu |
| Abstract | One of the main challenges of advancing task-oriented learning such as visual task planning and reinforcement learning is the lack of realistic and standardized environments for training and testing AI agents. Previously, researchers often relied on ad-hoc lab environments. There have been recent advances in virtual systems built with 3D physics engines and photo-realistic rendering for indoor and outdoor environments, but the embodied agents in those systems can only conduct simple interactions with the world (e.g., walking around, moving objects, etc.). Most of the existing systems also do not allow human participation in their simulated environments. In this work, we design and implement a virtual reality (VR) system, VRKitchen, with integrated functions which i) enable embodied agents powered by modern AI methods (e.g., planning, reinforcement learning, etc.) to perform complex tasks involving a wide range of fine-grained object manipulations in a realistic environment, and ii) allow human teachers to perform demonstrations to train agents (i.e., learning from demonstration). We also provide standardized evaluation benchmarks and data collection tools to facilitate a broad use in research on task-oriented learning and beyond. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05757v1 |
| http://arxiv.org/pdf/1903.05757v1.pdf | |
| PWC | https://paperswithcode.com/paper/vrkitchen-an-interactive-3d-virtual |
| Repo | |
| Framework | |
