Paper Group ANR 1409
A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning. Bayesian Optimisation with Gaussian Processes for Premise Selection. The Role of Artificial Intelligence (AI) in Adaptive eLearning System (AES) Content Formation: Risks and Opportunities involved. DeepPool: Distributed Model-free Algorithm for Ride …
A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning
| Title | A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning |
| Authors | Yixuan Lin, Kaiqing Zhang, Zhuoran Yang, Zhaoran Wang, Tamer Başar, Romeil Sandhu, Ji Liu |
| Abstract | This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectional communication relationships depicted by a directed graph. It is shown that the algorithm can solve the problem for strongly connected graphs by allowing each agent to transmit only two scalar-valued variables at one time. |
| Tasks | |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03053v1 |
| https://arxiv.org/pdf/1907.03053v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-communication-efficient-multi-agent-actor |
| Repo | |
| Framework | |
Bayesian Optimisation with Gaussian Processes for Premise Selection
| Title | Bayesian Optimisation with Gaussian Processes for Premise Selection |
| Authors | Agnieszka Słowik, Chaitanya Mangla, Mateja Jamnik, Sean B. Holden, Lawrence C. Paulson |
| Abstract | Heuristics in theorem provers are often parameterised. Modern theorem provers such as Vampire utilise a wide array of heuristics to control the search space explosion, thereby requiring optimisation of a large set of parameters. An exhaustive search in this multi-dimensional parameter space is intractable in most cases, yet the performance of the provers is highly dependent on the parameter assignment. In this work, we introduce a principled probablistic framework for heuristics optimisation in theorem provers. We present results using a heuristic for premise selection and The Archive of Formal Proofs (AFP) as a case study. |
| Tasks | Bayesian Optimisation, Gaussian Processes |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.09137v1 |
| https://arxiv.org/pdf/1909.09137v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimisation-with-gaussian-processes |
| Repo | |
| Framework | |
The Role of Artificial Intelligence (AI) in Adaptive eLearning System (AES) Content Formation: Risks and Opportunities involved
| Title | The Role of Artificial Intelligence (AI) in Adaptive eLearning System (AES) Content Formation: Risks and Opportunities involved |
| Authors | Suleiman Adamu, Jamilu Awwalu |
| Abstract | Artificial Intelligence (AI) plays varying roles in supporting both existing and emerging technologies. In the area of Learning and Tutoring, it plays key role in Intelligent Tutoring Systems (ITS). The fusion of ITS with Adaptive Hypermedia and Multimedia (AHAM) form the backbone of Adaptive eLearning Systems (AES) which provides personalized experiences to learners. This experience is important because it facilitates the accurate delivery of the learning modules in specific to the learner capacity and readiness. AES types vary, with Adaptive Web Based eLearning Systems (AWBES) being the popular type because of wider access offered by the web technology.The retrieval and aggregation of contents for any eLearning system is critical whichis determined by the relevance of learning material to the needs of the learner.In this paper, we discuss components of AES, role of AI in AES content aggregation, possible risks and available opportunities. |
| Tasks | |
| Published | 2019-03-03 |
| URL | http://arxiv.org/abs/1903.00934v1 |
| http://arxiv.org/pdf/1903.00934v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-role-of-artificial-intelligence-ai-in |
| Repo | |
| Framework | |
DeepPool: Distributed Model-free Algorithm for Ride-sharing using Deep Reinforcement Learning
| Title | DeepPool: Distributed Model-free Algorithm for Ride-sharing using Deep Reinforcement Learning |
| Authors | Abubakr Alabbasi, Arnob Ghosh, Vaneet Aggarwal |
| Abstract | The success of modern ride-sharing platforms crucially depends on the profit of the ride-sharing fleet operating companies, and how efficiently the resources are managed. Further, ride-sharing allows sharing costs and, hence, reduces the congestion and emission by making better use of vehicle capacities. In this work, we develop a distributed model-free, DeepPool, that uses deep Q-network (DQN) techniques to learn optimal dispatch policies by interacting with the environment. Further, DeepPool efficiently incorporates travel demand statistics and deep learning models to manage dispatching vehicles for improved ride sharing services. Using real-world dataset of taxi trip records in New York City, DeepPool performs better than other strategies, proposed in the literature, that do not consider ride sharing or do not dispatch the vehicles to regions where the future demand is anticipated. Finally, DeepPool can adapt rapidly to dynamic environments since it is implemented in a distributed manner in which each vehicle solves its own DQN individually without coordination. |
| Tasks | |
| Published | 2019-03-09 |
| URL | http://arxiv.org/abs/1903.03882v1 |
| http://arxiv.org/pdf/1903.03882v1.pdf | |
| PWC | https://paperswithcode.com/paper/deeppool-distributed-model-free-algorithm-for |
| Repo | |
| Framework | |
A High-Fidelity Open Embodied Avatar with Lip Syncing and Expression Capabilities
| Title | A High-Fidelity Open Embodied Avatar with Lip Syncing and Expression Capabilities |
| Authors | Deepali Aneja, Daniel McDuff, Shital Shah |
| Abstract | Embodied avatars as virtual agents have many applications and provide benefits over disembodied agents, allowing non-verbal social and interactional cues to be leveraged, in a similar manner to how humans interact with each other. We present an open embodied avatar built upon the Unreal Engine that can be controlled via a simple python programming interface. The avatar has lip syncing (phoneme control), head gesture and facial expression (using either facial action units or cardinal emotion categories) capabilities. We release code and models to illustrate how the avatar can be controlled like a puppet or used to create a simple conversational agent using public application programming interfaces (APIs). GITHUB link: https://github.com/danmcduff/AvatarSim |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08766v2 |
| https://arxiv.org/pdf/1909.08766v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-high-fidelity-open-embodied-avatar-with-lip |
| Repo | |
| Framework | |
Notes on Computational Hardness of Hypothesis Testing: Predictions using the Low-Degree Likelihood Ratio
| Title | Notes on Computational Hardness of Hypothesis Testing: Predictions using the Low-Degree Likelihood Ratio |
| Authors | Dmitriy Kunisky, Alexander S. Wein, Afonso S. Bandeira |
| Abstract | These notes survey and explore an emerging method, which we call the low-degree method, for predicting and understanding statistical-versus-computational tradeoffs in high-dimensional inference problems. In short, the method posits that a certain quantity – the second moment of the low-degree likelihood ratio – gives insight into how much computational time is required to solve a given hypothesis testing problem, which can in turn be used to predict the computational hardness of a variety of statistical inference tasks. While this method originated in the study of the sum-of-squares (SoS) hierarchy of convex programs, we present a self-contained introduction that does not require knowledge of SoS. In addition to showing how to carry out predictions using the method, we include a discussion investigating both rigorous and conjectural consequences of these predictions. These notes include some new results, simplified proofs, and refined conjectures. For instance, we point out a formal connection between spectral methods and the low-degree likelihood ratio, and we give a sharp low-degree lower bound against subexponential-time algorithms for tensor PCA. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11636v1 |
| https://arxiv.org/pdf/1907.11636v1.pdf | |
| PWC | https://paperswithcode.com/paper/notes-on-computational-hardness-of-hypothesis |
| Repo | |
| Framework | |
Homo Cyberneticus: The Era of Human-AI Integration
| Title | Homo Cyberneticus: The Era of Human-AI Integration |
| Authors | Jun Rekimoto |
| Abstract | This article is submitted and accepted as ACM UIST 2019 Visions. UIST Visions is a venue for forward thinking ideas to inspire the community. The goal is not to report research but to project and propose new research directions. This article, entitled “Homo Cyberneticus: The Era of Human-AI Integration”, proposes HCI research directions, namely human-augmentation and human-AI-integration. |
| Tasks | |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1911.02637v1 |
| https://arxiv.org/pdf/1911.02637v1.pdf | |
| PWC | https://paperswithcode.com/paper/homo-cyberneticus-the-era-of-human-ai |
| Repo | |
| Framework | |
A Unified Neural Coherence Model
| Title | A Unified Neural Coherence Model |
| Authors | Han Cheol Moon, Tasnim Mohiuddin, Shafiq Joty, Xu Chi |
| Abstract | Recently, neural approaches to coherence modeling have achieved state-of-the-art results in several evaluation tasks. However, we show that most of these models often fail on harder tasks with more realistic application scenarios. In particular, the existing models underperform on tasks that require the model to be sensitive to local contexts such as candidate ranking in conversational dialogue and in machine translation. In this paper, we propose a unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework. With extensive experiments on local and global discrimination tasks, we demonstrate that our proposed model outperforms existing models by a good margin, and establish a new state-of-the-art. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://arxiv.org/abs/1909.00349v1 |
| https://arxiv.org/pdf/1909.00349v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-neural-coherence-model |
| Repo | |
| Framework | |
Music theme recognition using CNN and self-attention
| Title | Music theme recognition using CNN and self-attention |
| Authors | Manoj Sukhavasi, Sainath Adapa |
| Abstract | We present an efficient architecture to detect mood/themes in music tracks on autotagging-moodtheme subset of the MTG-Jamendo dataset. Our approach consists of two blocks, a CNN block based on MobileNetV2 architecture and a self-attention block from Transformer architecture to capture long term temporal characteristics. We show that our proposed model produces a significant improvement over the baseline model. Our model (team name: AMLAG) achieves 4th place on PR-AUC-macro Leaderboard in MediaEval 2019: Emotion and Theme Recognition in Music Using Jamendo. |
| Tasks | |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.07041v1 |
| https://arxiv.org/pdf/1911.07041v1.pdf | |
| PWC | https://paperswithcode.com/paper/music-theme-recognition-using-cnn-and-self |
| Repo | |
| Framework | |
Spread-gram: A spreading-activation schema of network structural learning
| Title | Spread-gram: A spreading-activation schema of network structural learning |
| Authors | Jie Bai, Linjing Li, Daniel Zeng |
| Abstract | Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive model of human memory, we propose a network representation learning scheme. In this scheme, we learn node embeddings by adjusting the proximity of nodes traversing the spreading structure of the network. Our proposed method shows a significant improvement in multiple analysis tasks based on various real-world networks, ranging from semantic networks to protein interaction networks, international trade networks, human behavior networks, etc. In particular, our model can effectively discover the hierarchical structures in networks. The well-organized model training speeds up the convergence to only a small number of iterations, and the training time is linear with respect to the edge numbers. |
| Tasks | Representation Learning |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13581v1 |
| https://arxiv.org/pdf/1909.13581v1.pdf | |
| PWC | https://paperswithcode.com/paper/spread-gram-a-spreading-activation-schema-of |
| Repo | |
| Framework | |
Taming Reasoning in Temporal Probabilistic Relational Models
| Title | Taming Reasoning in Temporal Probabilistic Relational Models |
| Authors | Marcel Gehrke, Ralf Möller, Tanya Braun |
| Abstract | Evidence often grounds temporal probabilistic relational models over time, which makes reasoning infeasible. To counteract groundings over time and to keep reasoning polynomial by restoring a lifted representation, we present temporal approximate merging (TAMe), which incorporates (i) clustering for grouping submodels as well as (ii) statistical significance checks to test the fitness of the clustering outcome. In exchange for faster runtimes, TAMe introduces a bounded error that becomes negligible over time. Empirical results show that TAMe significantly improves the runtime performance of inference, while keeping errors small. |
| Tasks | |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.07040v1 |
| https://arxiv.org/pdf/1911.07040v1.pdf | |
| PWC | https://paperswithcode.com/paper/taming-reasoning-in-temporal-probabilistic |
| Repo | |
| Framework | |
Hindsight Generative Adversarial Imitation Learning
| Title | Hindsight Generative Adversarial Imitation Learning |
| Authors | Naijun Liu, Tao Lu, Yinghao Cai, Boyao Li, Shuo Wang |
| Abstract | Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising alternative is to train agent learning skills via imitation learning without expert demonstrations, which, to some extent, would extremely expand imitation learning areas. To achieve such expectation, in this paper, we propose Hindsight Generative Adversarial Imitation Learning (HGAIL) algorithm, with the aim of achieving imitation learning satisfying no need of demonstrations. Combining hindsight idea with the generative adversarial imitation learning (GAIL) framework, we realize implementing imitation learning successfully in cases of expert demonstration data are not available. Experiments show that the proposed method can train policies showing comparable performance to current imitation learning methods. Further more, HGAIL essentially endows curriculum learning mechanism which is critical for learning policies. |
| Tasks | Imitation Learning |
| Published | 2019-03-19 |
| URL | http://arxiv.org/abs/1903.07854v1 |
| http://arxiv.org/pdf/1903.07854v1.pdf | |
| PWC | https://paperswithcode.com/paper/hindsight-generative-adversarial-imitation |
| Repo | |
| Framework | |
Classical Music Prediction and Composition by means of Variational Autoencoders
| Title | Classical Music Prediction and Composition by means of Variational Autoencoders |
| Authors | Daniel Rivero, Enrique Fernandez-Blanco, Alejandro Pazos |
| Abstract | This paper proposes a new model for music prediction based on Variational Autoencoders (VAEs). In this work, VAEs are used in a novel way in order to address two different problems: music representation into the latent space, and using this representation to make predictions of the future values of the musical piece. This approach was trained with different songs of a classical composer. As a result, the system can represent the music in the latent space, and make accurate predictions. Therefore, the system can be used to compose new music either from an existing piece or from a random starting point. An additional feature of this system is that a small dataset was used for training. However, results show that the system is able to return accurate representations and predictions in unseen data. |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09972v1 |
| https://arxiv.org/pdf/1906.09972v1.pdf | |
| PWC | https://paperswithcode.com/paper/classical-music-prediction-and-composition-by |
| Repo | |
| Framework | |
Text-to-image synthesis method evaluation based on visual patterns
| Title | Text-to-image synthesis method evaluation based on visual patterns |
| Authors | William Lund Sommer, Alexandros Iosifidis |
| Abstract | A commonly used evaluation metric for text-to-image synthesis is the Inception score (IS) \cite{inceptionscore}, which has been shown to be a quality metric that correlates well with human judgment. However, IS does not reveal properties of the generated images indicating the ability of a text-to-image synthesis method to correctly convey semantics of the input text descriptions. In this paper, we introduce an evaluation metric and a visual evaluation method allowing for the simultaneous estimation of the realism, variety and semantic accuracy of generated images. The proposed method uses a pre-trained Inception network \cite{inceptionnet} to produce high dimensional representations for both real and generated images. These image representations are then visualized in a $2$-dimensional feature space defined by the t-distributed Stochastic Neighbor Embedding (t-SNE) \cite{tsne}. Visual concepts are determined by clustering the real image representations, and are subsequently used to evaluate the similarity of the generated images to the real ones by classifying them to the closest visual concept. The resulting classification accuracy is shown to be a effective gauge for the semantic accuracy of text-to-image synthesis methods. |
| Tasks | Image Generation |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1911.00077v1 |
| https://arxiv.org/pdf/1911.00077v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-to-image-synthesis-method-evaluation |
| Repo | |
| Framework | |
SPOCC: Scalable POssibilistic Classifier Combination – toward robust aggregation of classifiers
| Title | SPOCC: Scalable POssibilistic Classifier Combination – toward robust aggregation of classifiers |
| Authors | Mahmoud Albardan, John Klein, Olivier Colot |
| Abstract | We investigate a problem in which each member of a group of learners is trained separately to solve the same classification task. Each learner has access to a training dataset (possibly with overlap across learners) but each trained classifier can be evaluated on a validation dataset. We propose a new approach to aggregate the learner predictions in the possibility theory framework. For each classifier prediction, we build a possibility distribution assessing how likely the classifier prediction is correct using frequentist probabilities estimated on the validation set. The possibility distributions are aggregated using an adaptive t-norm that can accommodate dependency and poor accuracy of the classifier predictions. We prove that the proposed approach possesses a number of desirable classifier combination robustness properties. |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06475v2 |
| https://arxiv.org/pdf/1908.06475v2.pdf | |
| PWC | https://paperswithcode.com/paper/spocc-scalable-possibilistic-classifier |
| Repo | |
| Framework | |
