Paper Group ANR 15
Agent-Mediated Social Choice. Rank Projection Trees for Multilevel Neural Network Interpretation. Machine Learning in Official Statistics. Bayesian Semi-supervised Learning with Graph Gaussian Processes. Enrichment of OntoSenseNet: Adding a Sense-annotated Telugu lexicon. Algorithm Configuration: Learning policies for the quick termination of poor …
Agent-Mediated Social Choice
| Title | Agent-Mediated Social Choice |
| Authors | Umberto Grandi |
| Abstract | Direct democracy is often proposed as a possible solution to the 21st-century problems of democracy. However, this suggestion clashes with the size and complexity of 21st-century societies, entailing an excessive cognitive burden on voters, who would have to submit informed opinions on an excessive number of issues. In this paper I argue for the development of voting avatars, autonomous agents debating and voting on behalf of each citizen. Theoretical research from artificial intelligence, and in particular multiagent systems and computational social choice, proposes 21st-century techniques for this purpose, from the compact representation of a voter’s preferences and values, to the development of voting procedures for autonomous agents use only. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07199v2 |
| http://arxiv.org/pdf/1806.07199v2.pdf | |
| PWC | https://paperswithcode.com/paper/agent-mediated-social-choice |
| Repo | |
| Framework | |
Rank Projection Trees for Multilevel Neural Network Interpretation
| Title | Rank Projection Trees for Multilevel Neural Network Interpretation |
| Authors | Jonathan Warrell, Hussein Mohsen, Mark Gerstein |
| Abstract | A variety of methods have been proposed for interpreting nodes in deep neural networks, which typically involve scoring nodes at lower layers with respect to their effects on the output of higher-layer nodes (where lower and higher layers are closer to the input and output layers, respectively). However, we may be interested in picking out a prioritized collection of subsets of the inputs across a range of scales according to their importance for an output node, and not simply a prioritized ranking across the inputs as singletons. Such a situation may arise in biological applications, for instance, where we are interested in epistatic effects between groups of genes in determining a trait of interest. Here, we outline a flexible framework which may be used to generate multiscale network interpretations, using any previously defined scoring function. We demonstrate the ability of our method to pick out biologically important genes and gene sets in the domains of cancer and psychiatric genomics. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://arxiv.org/abs/1812.00172v1 |
| http://arxiv.org/pdf/1812.00172v1.pdf | |
| PWC | https://paperswithcode.com/paper/rank-projection-trees-for-multilevel-neural |
| Repo | |
| Framework | |
Machine Learning in Official Statistics
| Title | Machine Learning in Official Statistics |
| Authors | Martin Beck, Florian Dumpert, Joerg Feuerhake |
| Abstract | In the first half of 2018, the Federal Statistical Office of Germany (Destatis) carried out a “Proof of Concept Machine Learning” as part of its Digital Agenda. A major component of this was surveys on the use of machine learning methods in official statistics, which were conducted at selected national and international statistical institutions and among the divisions of Destatis. It was of particular interest to find out in which statistical areas and for which tasks machine learning is used and which methods are applied. This paper is intended to make the results of the surveys publicly accessible. |
| Tasks | |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.10422v1 |
| http://arxiv.org/pdf/1812.10422v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-in-official-statistics |
| Repo | |
| Framework | |
Bayesian Semi-supervised Learning with Graph Gaussian Processes
| Title | Bayesian Semi-supervised Learning with Graph Gaussian Processes |
| Authors | Yin Cheng Ng, Nicolo Colombo, Ricardo Silva |
| Abstract | We propose a data-efficient Gaussian process-based Bayesian approach to the semi-supervised learning problem on graphs. The proposed model shows extremely competitive performance when compared to the state-of-the-art graph neural networks on semi-supervised learning benchmark experiments, and outperforms the neural networks in active learning experiments where labels are scarce. Furthermore, the model does not require a validation data set for early stopping to control over-fitting. Our model can be viewed as an instance of empirical distribution regression weighted locally by network connectivity. We further motivate the intuitive construction of the model with a Bayesian linear model interpretation where the node features are filtered by an operator related to the graph Laplacian. The method can be easily implemented by adapting off-the-shelf scalable variational inference algorithms for Gaussian processes. |
| Tasks | Active Learning, Gaussian Processes |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04379v3 |
| http://arxiv.org/pdf/1809.04379v3.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-semi-supervised-learning-with-graph |
| Repo | |
| Framework | |
Enrichment of OntoSenseNet: Adding a Sense-annotated Telugu lexicon
| Title | Enrichment of OntoSenseNet: Adding a Sense-annotated Telugu lexicon |
| Authors | Sreekavitha Parupalli, Navjyoti Singh |
| Abstract | The paper describes the enrichment of OntoSenseNet - a verb-centric lexical resource for Indian Languages. This resource contains a newly developed Telugu-Telugu dictionary. It is important because native speakers can better annotate the senses when both the word and its meaning are in Telugu. Hence efforts are made to develop a soft copy of Telugu dictionary. Our resource also has manually annotated gold standard corpus consisting 8483 verbs, 253 adverbs and 1673 adjectives. Annotations are done by native speakers according to defined annotation guidelines. In this paper, we provide an overview of the annotation procedure and present the validation of our resource through inter-annotator agreement. Concepts of sense-class and sense-type are discussed. Additionally, we discuss the potential of lexical sense-annotated corpora in improving word sense disambiguation (WSD) tasks. Telugu WordNet is crowd-sourced for annotation of individual words in synsets and is compared with the developed sense-annotated lexicon (OntoSenseNet) to examine the improvement. Also, we present a special categorization (spatio-temporal classification) of adjectives. |
| Tasks | Word Sense Disambiguation |
| Published | 2018-04-06 |
| URL | http://arxiv.org/abs/1804.02186v2 |
| http://arxiv.org/pdf/1804.02186v2.pdf | |
| PWC | https://paperswithcode.com/paper/enrichment-of-ontosensenet-adding-a-sense |
| Repo | |
| Framework | |
Algorithm Configuration: Learning policies for the quick termination of poor performers
| Title | Algorithm Configuration: Learning policies for the quick termination of poor performers |
| Authors | Daniel Karapetyan, Andrew J. Parkes, Thomas Stützle |
| Abstract | One way to speed up the algorithm configuration task is to use short runs instead of long runs as much as possible, but without discarding the configurations that eventually do well on the long runs. We consider the problem of selecting the top performing configurations of the Conditional Markov Chain Search (CMCS), a general algorithm schema that includes, for examples, VNS. We investigate how the structure of performance on short tests links with those on long tests, showing that significant differences arise between test domains. We propose a “performance envelope” method to exploit the links; that learns when runs should be terminated, but that automatically adapts to the domain. |
| Tasks | |
| Published | 2018-03-26 |
| URL | http://arxiv.org/abs/1803.09785v1 |
| http://arxiv.org/pdf/1803.09785v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithm-configuration-learning-policies-for |
| Repo | |
| Framework | |
Long-term Multi-granularity Deep Framework for Driver Drowsiness Detection
| Title | Long-term Multi-granularity Deep Framework for Driver Drowsiness Detection |
| Authors | Jie Lyu, Zejian Yuan, Dapeng Chen |
| Abstract | For real-world driver drowsiness detection from videos, the variation of head pose is so large that the existing methods on global face is not capable of extracting effective features, such as looking aside and lowering head. Temporal dependencies with variable length are also rarely considered by the previous approaches, e.g., yawning and speaking. In this paper, we propose a Long-term Multi-granularity Deep Framework to detect driver drowsiness in driving videos containing the frontal faces. The framework includes two key components: (1) Multi-granularity Convolutional Neural Network (MCNN), a novel network utilizes a group of parallel CNN extractors on well-aligned facial patches of different granularities, and extracts facial representations effectively for large variation of head pose, furthermore, it can flexibly fuse both detailed appearance clues of the main parts and local to global spatial constraints; (2) a deep Long Short Term Memory network is applied on facial representations to explore long-term relationships with variable length over sequential frames, which is capable to distinguish the states with temporal dependencies, such as blinking and closing eyes. Our approach achieves 90.05% accuracy and about 37 fps speed on the evaluation set of the public NTHU-DDD dataset, which is the state-of-the-art method on driver drowsiness detection. Moreover, we build a new dataset named FI-DDD, which is of higher precision of drowsy locations in temporal dimension. |
| Tasks | |
| Published | 2018-01-08 |
| URL | http://arxiv.org/abs/1801.02325v1 |
| http://arxiv.org/pdf/1801.02325v1.pdf | |
| PWC | https://paperswithcode.com/paper/long-term-multi-granularity-deep-framework |
| Repo | |
| Framework | |
Bandits with Temporal Stochastic Constraints
| Title | Bandits with Temporal Stochastic Constraints |
| Authors | Priyank Agrawal, Theja Tulabandhula |
| Abstract | We study the effect of impairment on stochastic multi-armed bandits and develop new ways to mitigate it. Impairment effect is the phenomena where an agent only accrues reward for an action if they have played it at least a few times in the recent past. It is practically motivated by repetition and recency effects in domains such as advertising (here consumer behavior may require repeat actions by advertisers) and vocational training (here actions are complex skills that can only be mastered with repetition to get a payoff). Impairment can be naturally modelled as a temporal constraint on the strategy space, and we provide two novel algorithms that achieve sublinear regret, each working with different assumptions on the impairment effect. We introduce a new notion called bucketing in our algorithm design, and show how it can effectively address impairment as well as a broader class of temporal constraints. Our regret bounds explicitly capture the cost of impairment and show that it scales (sub-)linearly with the degree of impairment. Our work complements recent work on modeling delays and corruptions, and we provide experimental evidence supporting our claims. |
| Tasks | Multi-Armed Bandits |
| Published | 2018-11-22 |
| URL | http://arxiv.org/abs/1811.09026v1 |
| http://arxiv.org/pdf/1811.09026v1.pdf | |
| PWC | https://paperswithcode.com/paper/bandits-with-temporal-stochastic-constraints |
| Repo | |
| Framework | |
Self Paced Adversarial Training for Multimodal Few-shot Learning
| Title | Self Paced Adversarial Training for Multimodal Few-shot Learning |
| Authors | Frederik Pahde, Oleksiy Ostapenko, Patrick Jähnichen, Tassilo Klein, Moin Nabi |
| Abstract | State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks. However, they still fail to provide satisfactory results in scarce data regimes. To a certain extent this lack of data can be compensated by multimodal information. Missing information in one modality of a single data point (e.g. an image) can be made up for in another modality (e.g. a textual description). Therefore, we design a few-shot learning task that is multimodal during training (i.e. image and text) and single-modal during test time (i.e. image). In this regard, we propose a self-paced class-discriminative generative adversarial network incorporating multimodality in the context of few-shot learning. The proposed approach builds upon the idea of cross-modal data generation in order to alleviate the data sparsity problem. We improve few-shot learning accuracies on the finegrained CUB and Oxford-102 datasets. |
| Tasks | Few-Shot Learning |
| Published | 2018-11-22 |
| URL | http://arxiv.org/abs/1811.09192v1 |
| http://arxiv.org/pdf/1811.09192v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-paced-adversarial-training-for |
| Repo | |
| Framework | |
Maximum a Posteriori Policy Optimisation
| Title | Maximum a Posteriori Policy Optimisation |
| Authors | Abbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa, Remi Munos, Nicolas Heess, Martin Riedmiller |
| Abstract | We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are competitive with the state-of-the-art in deep reinforcement learning. In particular, for continuous control, our method outperforms existing methods with respect to sample efficiency, premature convergence and robustness to hyperparameter settings while achieving similar or better final performance. |
| Tasks | Continuous Control |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.06920v1 |
| http://arxiv.org/pdf/1806.06920v1.pdf | |
| PWC | https://paperswithcode.com/paper/maximum-a-posteriori-policy-optimisation |
| Repo | |
| Framework | |
Effect of antipsychotics on community structure in functional brain networks
| Title | Effect of antipsychotics on community structure in functional brain networks |
| Authors | Ryan Flanagan, Lucas Lacasa, Emma K. Towlson, Sang Hoon Lee, Mason A. Porter |
| Abstract | Schizophrenia, a mental disorder that is characterized by abnormal social behavior and failure to distinguish one’s own thoughts and ideas from reality, has been associated with structural abnormalities in the architecture of functional brain networks. Using various methods from network analysis, we examine the effect of two classical therapeutic antipsychotics — Aripiprazole and Sulpiride — on the structure of functional brain networks of healthy controls and patients who have been diagnosed with schizophrenia. We compare the community structures of functional brain networks of different individuals using mesoscopic response functions, which measure how community structure changes across different scales of a network. We are able to do a reasonably good job of distinguishing patients from controls, and we are most successful at this task on people who have been treated with Aripiprazole. We demonstrate that this increased separation between patients and controls is related only to a change in the control group, as the functional brain networks of the patient group appear to be predominantly unaffected by this drug. This suggests that Aripiprazole has a significant and measurable effect on community structure in healthy individuals but not in individuals who are diagnosed with schizophrenia. In contrast, we find for individuals are given the drug Sulpiride that it is more difficult to separate the networks of patients from those of controls. Overall, we observe differences in the effects of the drugs (and a placebo) on community structure in patients and controls and also that this effect differs across groups. We thereby demonstrate that different types of antipsychotic drugs selectively affect mesoscale structures of brain networks, providing support that mesoscale structures such as communities are meaningful functional units in the brain. |
| Tasks | |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1806.00080v2 |
| http://arxiv.org/pdf/1806.00080v2.pdf | |
| PWC | https://paperswithcode.com/paper/effect-of-antipsychotics-on-community |
| Repo | |
| Framework | |
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
| Title | Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction |
| Authors | Longlong Jing, Xiaodong Yang, Jingen Liu, Yingli Tian |
| Abstract | The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose 3DRotNet: a fully self-supervised approach to learn spatiotemporal features from unlabeled videos. A set of rotations are applied to all videos, and a pretext task is defined as prediction of these rotations. When accomplishing this task, 3DRotNet is actually trained to understand the semantic concepts and motions in videos. In other words, it learns a spatiotemporal video representation, which can be transferred to improve video understanding tasks in small datasets. Our extensive experiments successfully demonstrate the effectiveness of the proposed framework on action recognition, leading to significant improvements over the state-of-the-art self-supervised methods. With the self-supervised pre-trained 3DRotNet from large datasets, the recognition accuracy is boosted up by 20.4% on UCF101 and 16.7% on HMDB51 respectively, compared to the models trained from scratch. |
| Tasks | Temporal Action Localization, Video Understanding |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11387v2 |
| http://arxiv.org/pdf/1811.11387v2.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-spatiotemporal-feature |
| Repo | |
| Framework | |
Person-Job Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning
| Title | Person-Job Fit: Adapting the Right Talent for the Right Job with Joint Representation Learning |
| Authors | Chen Zhu, Hengshu Zhu, Hui Xiong, Chao Ma, Fang Xie, Pengliang Ding, Pan Li |
| Abstract | Person-Job Fit is the process of matching the right talent for the right job by identifying talent competencies that are required for the job. While many qualitative efforts have been made in related fields, it still lacks of quantitative ways of measuring talent competencies as well as the job’s talent requirements. To this end, in this paper, we propose a novel end-to-end data-driven model based on Convolutional Neural Network (CNN), namely Person-Job Fit Neural Network (PJFNN), for matching a talent qualification to the requirements of a job. To be specific, PJFNN is a bipartite neural network which can effectively learn the joint representation of Person-Job fitness from historical job applications. In particular, due to the design of a hierarchical representation structure, PJFNN can not only estimate whether a candidate fits a job, but also identify which specific requirement items in the job posting are satisfied by the candidate by measuring the distances between corresponding latent representations. Finally, the extensive experiments on a large-scale real-world dataset clearly validate the performance of PJFNN in terms of Person-Job Fit prediction. Also, we provide effective data visualization to show some job and talent benchmark insights obtained by PJFNN. |
| Tasks | Representation Learning |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.04040v1 |
| http://arxiv.org/pdf/1810.04040v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-job-fit-adapting-the-right-talent-for |
| Repo | |
| Framework | |
Hierarchical CVAE for Fine-Grained Hate Speech Classification
| Title | Hierarchical CVAE for Fine-Grained Hate Speech Classification |
| Authors | Jing Qian, Mai ElSherief, Elizabeth Belding, William Yang Wang |
| Abstract | Existing work on automated hate speech detection typically focuses on binary classification or on differentiating among a small set of categories. In this paper, we propose a novel method on a fine-grained hate speech classification task, which focuses on differentiating among 40 hate groups of 13 different hate group categories. We first explore the Conditional Variational Autoencoder (CVAE) as a discriminative model and then extend it to a hierarchical architecture to utilize the additional hate category information for more accurate prediction. Experimentally, we show that incorporating the hate category information for training can significantly improve the classification performance and our proposed model outperforms commonly-used discriminative models. |
| Tasks | Hate Speech Detection |
| Published | 2018-08-31 |
| URL | http://arxiv.org/abs/1809.00088v1 |
| http://arxiv.org/pdf/1809.00088v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-cvae-for-fine-grained-hate |
| Repo | |
| Framework | |
A Decision-theoretic Approach to Detection-based Target Search with a UAV
| Title | A Decision-theoretic Approach to Detection-based Target Search with a UAV |
| Authors | Aayush Gupta, Daniel Bessonov, Patrick Li |
| Abstract | Search and rescue missions and surveillance require finding targets in a large area. These tasks often use unmanned aerial vehicles (UAVs) with cameras to detect and move towards a target. However, common UAV approaches make two simplifying assumptions. First, they assume that observations made from different heights are deterministically correct. In practice, observations are noisy, with the noise increasing as the height used for observations increases. Second, they assume that a motion command executes correctly, which may not happen due to wind and other environmental factors. To address these, we propose a sequential algorithm that determines actions in real time based on observations, using partially observable Markov decision processes (POMDPs). Our formulation handles both observations and motion uncertainty and errors. We run offline simulations and learn a policy. This policy is run on a UAV to find the target efficiently. We employ a novel compact formulation to represent the coordinates of the drone relative to the target coordinates. Our POMDP policy finds the target up to 3.4 times faster when compared to a heuristic policy. |
| Tasks | |
| Published | 2018-01-04 |
| URL | http://arxiv.org/abs/1801.01228v1 |
| http://arxiv.org/pdf/1801.01228v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-decision-theoretic-approach-to-detection |
| Repo | |
| Framework | |
