Paper Group ANR 971
Experience Management in Multi-player Games. Object Placement on Cluttered Surfaces: A Nested Local Search Approach. Directed Exploration for Reinforcement Learning. Self-Supervised Exploration via Disagreement. Parallel Computation of Graph Embeddings. Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy. Compare M …
Experience Management in Multi-player Games
| Title | Experience Management in Multi-player Games |
| Authors | Jichen Zhu, Santiago Ontañón |
| Abstract | Experience Management studies AI systems that automatically adapt interactive experiences such as games to tailor to specific players and to fulfill design goals. Although it has been explored for several decades, existing work in experience management has mostly focused on single-player experiences. This paper is a first attempt at identifying the main challenges to expand EM to multi-player/multi-user games or experiences. We also make connections to related areas where solutions for similar problems have been proposed (especially group recommender systems) and discusses the potential impact and applications of multi-player EM. |
| Tasks | Recommendation Systems |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1907.02349v1 |
| https://arxiv.org/pdf/1907.02349v1.pdf | |
| PWC | https://paperswithcode.com/paper/experience-management-in-multi-player-games |
| Repo | |
| Framework | |
Object Placement on Cluttered Surfaces: A Nested Local Search Approach
| Title | Object Placement on Cluttered Surfaces: A Nested Local Search Approach |
| Authors | Abdul Rahman Dabbour, Esra Erdem, Volkan Patoglu |
| Abstract | For planning rearrangements of objects in a clutter, it is required to know the goal configuration of the objects. However, in real life scenarios, this information is not available most of the time. We introduce a novel method that computes a collision-free placement of objects on a cluttered surface, while minimizing the total number and amount of displacements of the existing moveable objects. Our method applies nested local searches that perform multi-objective optimizations guided by heuristics. Experimental evaluations demonstrate high computational efficiency and success rate of our method, as well as good quality of solutions. |
| Tasks | |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08494v1 |
| https://arxiv.org/pdf/1906.08494v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-placement-on-cluttered-surfaces-a |
| Repo | |
| Framework | |
Directed Exploration for Reinforcement Learning
| Title | Directed Exploration for Reinforcement Learning |
| Authors | Zhaohan Daniel Guo, Emma Brunskill |
| Abstract | Efficient exploration is necessary to achieve good sample efficiency for reinforcement learning in general. From small, tabular settings such as gridworlds to large, continuous and sparse reward settings such as robotic object manipulation tasks, exploration through adding an uncertainty bonus to the reward function has been shown to be effective when the uncertainty is able to accurately drive exploration towards promising states. However reward bonuses can still be inefficient since they are non-stationary, which means that we must wait for function approximators to catch up and converge again when uncertainties change. We propose the idea of directed exploration, that is learning a goal-conditioned policy where goals are simply other states, and using that to directly try to reach states with large uncertainty. The goal-conditioned policy is independent of uncertainty and is thus stationary. We show in our experiments how directed exploration is more efficient at exploration and more robust to how the uncertainty is computed than adding bonuses to rewards. |
| Tasks | Efficient Exploration |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07805v1 |
| https://arxiv.org/pdf/1906.07805v1.pdf | |
| PWC | https://paperswithcode.com/paper/directed-exploration-for-reinforcement |
| Repo | |
| Framework | |
Self-Supervised Exploration via Disagreement
| Title | Self-Supervised Exploration via Disagreement |
| Authors | Deepak Pathak, Dhiraj Gandhi, Abhinav Gupta |
| Abstract | Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck in environments with stochastic dynamics or are too inefficient to be scalable to real robotics setups. In this paper, we propose a formulation for exploration inspired by the work in active learning literature. Specifically, we train an ensemble of dynamics models and incentivize the agent to explore such that the disagreement of those ensembles is maximized. This allows the agent to learn skills by exploring in a self-supervised manner without any external reward. Notably, we further leverage the disagreement objective to optimize the agent’s policy in a differentiable manner, without using reinforcement learning, which results in a sample-efficient exploration. We demonstrate the efficacy of this formulation across a variety of benchmark environments including stochastic-Atari, Mujoco and Unity. Finally, we implement our differentiable exploration on a real robot which learns to interact with objects completely from scratch. Project videos and code are at https://pathak22.github.io/exploration-by-disagreement/ |
| Tasks | Active Learning, Efficient Exploration |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04161v1 |
| https://arxiv.org/pdf/1906.04161v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-exploration-via-disagreement |
| Repo | |
| Framework | |
Parallel Computation of Graph Embeddings
| Title | Parallel Computation of Graph Embeddings |
| Authors | Chi Thang Duong, Hongzhi Yin, Thanh Dat Hoang, Truong Giang Le Ba, Matthias Weidlich, Quoc Viet Hung Nguyen, Karl Aberer |
| Abstract | Graph embedding aims at learning a vector-based representation of vertices that incorporates the structure of the graph. This representation then enables inference of graph properties. Existing graph embedding techniques, however, do not scale well to large graphs. We therefore propose a framework for parallel computation of a graph embedding using a cluster of compute nodes with resource constraints. We show how to distribute any existing embedding technique by first splitting a graph for any given set of constrained compute nodes and then reconciling the embedding spaces derived for these subgraphs. We also propose a new way to evaluate the quality of graph embeddings that is independent of a specific inference task. Based thereon, we give a formal bound on the difference between the embeddings derived by centralised and parallel computation. Experimental results illustrate that our approach for parallel computation scales well, while largely maintaining the embedding quality. |
| Tasks | Graph Embedding |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02977v1 |
| https://arxiv.org/pdf/1909.02977v1.pdf | |
| PWC | https://paperswithcode.com/paper/parallel-computation-of-graph-embeddings |
| Repo | |
| Framework | |
Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy
| Title | Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy |
| Authors | Ruihan Yang, Qiwei Ye, Tie-Yan Liu |
| Abstract | A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both efficiency and efficacy of the learning process. However, Existing works for exploration involve task-agnostic design, that is performing well in one environment, but be ill-suited to another. To the purpose of learning an effective and efficient exploration policy in an automated manner. We formalized a feasible metric for measuring the utility of exploration based on counterfactual ideology. Based on that, We proposed an end-to-end algorithm to learn exploration policy by meta-learning. We demonstrate that our method achieves good results compared to previous works in the high-dimensional control tasks in MuJoCo simulator. |
| Tasks | Efficient Exploration, Meta-Learning |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11583v1 |
| https://arxiv.org/pdf/1905.11583v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-efficient-and-effective-exploration |
| Repo | |
| Framework | |
Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning
| Title | Compare More Nuanced:Pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning |
| Authors | Huaxi Huang, Junjie Zhang, Jian Zhang, Qiang Wu, Jingsong Xu |
| Abstract | The recognition ability of human beings is developed in a progressive way. Usually, children learn to discriminate various objects from coarse to fine-grained with limited supervision. Inspired by this learning process, we propose a simple yet effective model for the Few-Shot Fine-Grained (FSFG) recognition, which tries to tackle the challenging fine-grained recognition task using meta-learning. The proposed method, named Pairwise Alignment Bilinear Network (PABN), is an end-to-end deep neural network. Unlike traditional deep bilinear networks for fine-grained classification, which adopt the self-bilinear pooling to capture the subtle features of images, the proposed model uses a novel pairwise bilinear pooling to compare the nuanced differences between base images and query images for learning a deep distance metric. In order to match base image features with query image features, we design feature alignment losses before the proposed pairwise bilinear pooling. Experiment results on four fine-grained classification datasets and one generic few-shot dataset demonstrate that the proposed model outperforms both the state-ofthe-art few-shot fine-grained and general few-shot methods. |
| Tasks | Meta-Learning |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03580v2 |
| http://arxiv.org/pdf/1904.03580v2.pdf | |
| PWC | https://paperswithcode.com/paper/compare-more-nuancedpairwise-alignment |
| Repo | |
| Framework | |
Dissecting Pruned Neural Networks
| Title | Dissecting Pruned Neural Networks |
| Authors | Jonathan Frankle, David Bau |
| Abstract | Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural networks by an order of magnitude without compromising accuracy, meaning these networks contain a vast amount of unnecessary structure. In this paper, we study the relationship between pruning and interpretability. Namely, we consider the effect of removing unnecessary structure on the number of hidden units that learn disentangled representations of human-recognizable concepts as identified by network dissection. We aim to evaluate how the interpretability of pruned neural networks changes as they are compressed. We find that pruning has no detrimental effect on this measure of interpretability until so few parameters remain that accuracy beings to drop. Resnet-50 models trained on ImageNet maintain the same number of interpretable concepts and units until more than 90% of parameters have been pruned. |
| Tasks | |
| Published | 2019-06-29 |
| URL | https://arxiv.org/abs/1907.00262v1 |
| https://arxiv.org/pdf/1907.00262v1.pdf | |
| PWC | https://paperswithcode.com/paper/dissecting-pruned-neural-networks |
| Repo | |
| Framework | |
USTAR: Online Multimodal Embedding for Modeling User-Guided Spatiotemporal Activity
| Title | USTAR: Online Multimodal Embedding for Modeling User-Guided Spatiotemporal Activity |
| Authors | Amila Silva, Shanika Karunasekera, Christopher Leckie, Ling Luo |
| Abstract | Building spatiotemporal activity models for people’s activities in urban spaces is important for understanding the ever-increasing complexity of urban dynamics. With the emergence of Geo-Tagged Social Media (GTSM) records, previous studies demonstrate the potential of GTSM records for spatiotemporal activity modeling. State-of-the-art methods for this task embed different modalities (location, time, and text) of GTSM records into a single embedding space. However, they ignore Non-GeoTagged Social Media (NGTSM) records, which generally account for the majority of posts (e.g., more than 95% in Twitter), and could represent a great source of information to alleviate the sparsity of GTSM records. Furthermore, in the current spatiotemporal embedding techniques, less focus has been given to the users, who exhibit spatially motivated behaviors. To bridge this research gap, this work proposes USTAR, a novel online learning method for User-guided SpatioTemporal Activity Representation, which (1) embeds locations, time, and text along with users into the same embedding space to capture their correlations; (2) uses a novel collaborative filtering approach based on two different empirically studied user behaviors to incorporate both NGTSM and GTSM records in learning; and (3) introduces a novel sampling technique to learn spatiotemporal representations in an online fashion to accommodate recent information into the embedding space, while avoiding overfitting to recent records and frequently appearing units in social media streams. Our results show that USTAR substantially improves the state-of-the-art for region retrieval and keyword retrieval and its potential to be applied to other downstream applications such as local event detection. |
| Tasks | |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10335v1 |
| https://arxiv.org/pdf/1910.10335v1.pdf | |
| PWC | https://paperswithcode.com/paper/ustar-online-multimodal-embedding-for |
| Repo | |
| Framework | |
Learning to Recommend Third-Party Library Migration Opportunities at the API Level
| Title | Learning to Recommend Third-Party Library Migration Opportunities at the API Level |
| Authors | Hussein Alrubaye, Mohamed Wiem Mkaouer, Igor Khokhlov, Leon Reznik, Ali Ouni, Jason Mcgoff |
| Abstract | The manual migration between different third-party libraries represents a challenge for software developers. Developers typically need to explore both libraries Application Programming Interfaces, along with reading their documentation, in order to locate the suitable mappings between replacing and replaced methods. In this paper, we introduce RAPIM, a novel machine learning approach that recommends mappings between methods from two different libraries. Our model learns from previous migrations, manually performed in mined software systems, and extracts a set of features related to the similarity between method signatures and method textual documentation. We evaluate our model using 8 popular migrations, collected from 57,447 open-source Java projects. Results show that RAPIM is able to recommend relevant library API mappings with an average accuracy score of 87%. Finally, we provide the community with an API recommendation web service that could be used to support the migration process. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.02882v1 |
| https://arxiv.org/pdf/1906.02882v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-recommend-third-party-library |
| Repo | |
| Framework | |
CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations
| Title | CHEETAH: An Ultra-Fast, Approximation-Free, and Privacy-Preserved Neural Network Framework based on Joint Obscure Linear and Nonlinear Computations |
| Authors | Qiao Zhang, Cong Wang, Chunsheng Xin, Hongyi Wu |
| Abstract | Machine Learning as a Service (MLaaS) is enabling a wide range of smart applications on end devices. However, such convenience comes with a cost of privacy because users have to upload their private data to the cloud. This research aims to provide effective and efficient MLaaS such that the cloud server learns nothing about user data and the users cannot infer the proprietary model parameters owned by the server. This work makes the following contributions. First, it unveils the fundamental performance bottleneck of existing schemes due to the heavy permutations in computing linear transformation and the use of communication intensive Garbled Circuits for nonlinear transformation. Second, it introduces an ultra-fast secure MLaaS framework, CHEETAH, which features a carefully crafted secret sharing scheme that runs significantly faster than existing schemes without accuracy loss. Third, CHEETAH is evaluated on the benchmark of well-known, practical deep networks such as AlexNet and VGG-16 on the MNIST and ImageNet datasets. The results demonstrate more than 100x speedup over the fastest GAZELLE (Usenix Security’18), 2000x speedup over MiniONN (ACM CCS’17) and five orders of magnitude speedup over CryptoNets (ICML’16). This significant speedup enables a wide range of practical applications based on privacy-preserved deep neural networks. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.05184v1 |
| https://arxiv.org/pdf/1911.05184v1.pdf | |
| PWC | https://paperswithcode.com/paper/cheetah-an-ultra-fast-approximation-free-and |
| Repo | |
| Framework | |
Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars
| Title | Comparing Multi-class, Binary and Hierarchical Machine Learning Classification schemes for variable stars |
| Authors | Zafiirah Hosenie, Robert Lyon, Benjamin Stappers, Arrykrishna Mootoovaloo |
| Abstract | Upcoming synoptic surveys are set to generate an unprecedented amount of data. This requires an automatic framework that can quickly and efficiently provide classification labels for several new object classification challenges. Using data describing 11 types of variable stars from the Catalina Real-Time Transient Surveys (CRTS), we illustrate how to capture the most important information from computed features and describe detailed methods of how to robustly use Information Theory for feature selection and evaluation. We apply three Machine Learning (ML) algorithms and demonstrate how to optimize these classifiers via cross-validation techniques. For the CRTS dataset, we find that the Random Forest (RF) classifier performs best in terms of balanced-accuracy and geometric means. We demonstrate substantially improved classification results by converting the multi-class problem into a binary classification task, achieving a balanced-accuracy rate of $\sim$99 per cent for the classification of ${\delta}$-Scuti and Anomalous Cepheids (ACEP). Additionally, we describe how classification performance can be improved via converting a ‘flat-multi-class’ problem into a hierarchical taxonomy. We develop a new hierarchical structure and propose a new set of classification features, enabling the accurate identification of subtypes of cepheids, RR Lyrae and eclipsing binary stars in CRTS data. |
| Tasks | Feature Selection, Object Classification |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.08189v1 |
| https://arxiv.org/pdf/1907.08189v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparing-multi-class-binary-and-hierarchical |
| Repo | |
| Framework | |
Dungeon Crawl Stone Soup as an Evaluation Domain for Artificial Intelligence
| Title | Dungeon Crawl Stone Soup as an Evaluation Domain for Artificial Intelligence |
| Authors | Dustin Dannenhauer, Michael W. Floyd, Jonathan Decker, David W. Aha |
| Abstract | Dungeon Crawl Stone Soup is a popular, single-player, free and open-source rogue-like video game with a sufficiently complex decision space that makes it an ideal testbed for research in cognitive systems and, more generally, artificial intelligence. This paper describes the properties of Dungeon Crawl Stone Soup that are conducive to evaluating new approaches of AI systems. We also highlight an ongoing effort to build an API for AI researchers in the spirit of recent game APIs such as MALMO, ELF, and the Starcraft II API. Dungeon Crawl Stone Soup’s complexity offers significant opportunities for evaluating AI and cognitive systems, including human user studies. In this paper we provide (1) a description of the state space of Dungeon Crawl Stone Soup, (2) a description of the components for our API, and (3) the potential benefits of evaluating AI agents in the Dungeon Crawl Stone Soup video game. |
| Tasks | Starcraft, Starcraft II |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01769v1 |
| http://arxiv.org/pdf/1902.01769v1.pdf | |
| PWC | https://paperswithcode.com/paper/dungeon-crawl-stone-soup-as-an-evaluation |
| Repo | |
| Framework | |
Attributed Sequence Embedding
| Title | Attributed Sequence Embedding |
| Authors | Zhongfang Zhuang, Xiangnan Kong, Elke Rundensteiner, Jihane Zouaoui, Aditya Arora |
| Abstract | Mining tasks over sequential data, such as clickstreams and gene sequences, require a careful design of embeddings usable by learning algorithms. Recent research in feature learning has been extended to sequential data, where each instance consists of a sequence of heterogeneous items with a variable length. However, many real-world applications often involve attributed sequences, where each instance is composed of both a sequence of categorical items and a set of attributes. In this paper, we study this new problem of attributed sequence embedding, where the goal is to learn the representations of attributed sequences in an unsupervised fashion. This problem is core to many important data mining tasks ranging from user behavior analysis to the clustering of gene sequences. This problem is challenging due to the dependencies between sequences and their associated attributes. We propose a deep multimodal learning framework, called NAS, to produce embeddings of attributed sequences. The embeddings are task independent and can be used on various mining tasks of attributed sequences. We demonstrate the effectiveness of our embeddings of attributed sequences in various unsupervised learning tasks on real-world datasets. |
| Tasks | |
| Published | 2019-11-03 |
| URL | https://arxiv.org/abs/1911.00949v1 |
| https://arxiv.org/pdf/1911.00949v1.pdf | |
| PWC | https://paperswithcode.com/paper/attributed-sequence-embedding |
| Repo | |
| Framework | |
Integration of Regularized l1 Tracking and Instance Segmentation for Video Object Tracking
| Title | Integration of Regularized l1 Tracking and Instance Segmentation for Video Object Tracking |
| Authors | Filiz Gurkan, Bilge Gunsel |
| Abstract | We introduce a tracking-by-detection method that integrates a deep object detector with a particle filter tracker under the regularization framework where the tracked object is represented by a sparse dictionary. A novel observation model which establishes consensus between the detector and tracker is formulated that enables us to update the dictionary with the guidance of the deep detector. This yields an efficient representation of the object appearance through the video sequence hence improves robustness to occlusion and pose changes. Moreover we propose a new state vector consisting of translation, rotation, scaling and shearing parameters that allows tracking the deformed object bounding boxes hence significantly increases robustness to scale changes. Numerical results reported on challenging VOT2016 and VOT2018 benchmarking data sets demonstrate that the introduced tracker, L1DPF-M, achieves comparable robustness on both data sets while it outperforms state-of-the-art trackers on both data sets where the improvement achieved in success rate at IoU-th=0.5 is 11% and 9%, respectively. |
| Tasks | Instance Segmentation, Object Tracking, Semantic Segmentation, Video Object Tracking |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12883v1 |
| https://arxiv.org/pdf/1912.12883v1.pdf | |
| PWC | https://paperswithcode.com/paper/integration-of-regularized-l1-tracking-and |
| Repo | |
| Framework | |
