April 1, 2020

3087 words 15 mins read

Paper Group ANR 508

Modelling Latent Skills for Multitask Language Generation. Question Type Classification Methods Comparison. Generalizing Face Representation with Unlabeled Data. Interpretable Multi Time-scale Constraints in Model-free Deep Reinforcement Learning for Autonomous Driving. From Statistical Relational to Neuro-Symbolic Artificial Intelligence. A Compac …

Modelling Latent Skills for Multitask Language Generation


Title	Modelling Latent Skills for Multitask Language Generation
Authors	Kris Cao, Dani Yogatama
Abstract	We present a generative model for multitask conditional language generation. Our guiding hypothesis is that a shared set of latent skills underlies many disparate language generation tasks, and that explicitly modelling these skills in a task embedding space can help with both positive transfer across tasks and with efficient adaptation to new tasks. We instantiate this task embedding space as a latent variable in a latent variable sequence-to-sequence model. We evaluate this hypothesis by curating a series of monolingual text-to-text language generation datasets - covering a broad range of tasks and domains - and comparing the performance of models both in the multitask and few-shot regimes. We show that our latent task variable model outperforms other sequence-to-sequence baselines on average across tasks in the multitask setting. In the few-shot learning setting on an unseen test dataset (i.e., a new task), we demonstrate that model adaptation based on inference in the latent task space is more robust than standard fine-tuning based parameter adaptation and performs comparably in terms of overall performance. Finally, we examine the latent task representations learnt by our model and show that they cluster tasks in a natural way.
Tasks	Few-Shot Learning, Text Generation
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09543v1
PDF	https://arxiv.org/pdf/2002.09543v1.pdf
PWC	https://paperswithcode.com/paper/modelling-latent-skills-for-multitask
Repo
Framework

Question Type Classification Methods Comparison


Title	Question Type Classification Methods Comparison
Authors	Tamirlan Seidakhmetov
Abstract	The paper presents a comparative study of state-of-the-art approaches for question classification task: Logistic Regression, Convolutional Neural Networks (CNN), Long Short-Term Memory Network (LSTM) and Quasi-Recurrent Neural Networks (QRNN). All models use pre-trained GLoVe word embeddings and trained on human-labeled data. The best accuracy is achieved using CNN model with five convolutional layers and various kernel sizes stacked in parallel, followed by one fully connected layer. The model reached 90.7% accuracy on TREC 10 test set. All the model architectures in this paper were developed from scratch on PyTorch, in few cases based on reliable open-source implementation.
Tasks	Word Embeddings
Published	2020-01-03
URL	https://arxiv.org/abs/2001.00571v1
PDF	https://arxiv.org/pdf/2001.00571v1.pdf
PWC	https://paperswithcode.com/paper/question-type-classification-methods
Repo
Framework

Generalizing Face Representation with Unlabeled Data


Title	Generalizing Face Representation with Unlabeled Data
Authors	Yichun Shi, Anil K. Jain
Abstract	In recent years, significant progress has been made in face recognition due to the availability of large-scale labeled face datasets. However, since the faces in these datasets usually contain limited degree and types of variation, the models trained on them generalize poorly to more realistic unconstrained face datasets. While collecting labeled faces with larger variations could be helpful, it is practically infeasible due to privacy and labor cost. In comparison, it is easier to acquire a large number of unlabeled faces from different domains which would better represent the testing scenarios in real-world problems. We present an approach to use such unlabeled faces to learn generalizable face representations, which can be viewed as an unsupervised domain generalization framework. Experimental results on unconstrained datasets show that a small amount of unlabeled data with sufficient diversity can (i) lead to an appreciable gain in recognition performance and (ii) outperform the supervised baseline when combined with less than half of the labeled data. Compared with the state-of-the-art face recognition methods, our method further improves their performance on challenging benchmarks, such as IJB-B, IJB-C and IJB-S.
Tasks	Domain Generalization, Face Recognition
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07936v1
PDF	https://arxiv.org/pdf/2003.07936v1.pdf
PWC	https://paperswithcode.com/paper/generalizing-face-representation-with
Repo
Framework

Interpretable Multi Time-scale Constraints in Model-free Deep Reinforcement Learning for Autonomous Driving


Title	Interpretable Multi Time-scale Constraints in Model-free Deep Reinforcement Learning for Autonomous Driving
Authors	Gabriel Kalweit, Maria Huegle, Moritz Werling, Joschka Boedecker
Abstract	In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of different objectives in the reward signal, or Lagrangian methods, including constraints in the loss function, have no guarantees that the agent satisfies the constraints at all points in time and lack in interpretability. When a discrete policy is extracted from an action-value function, safe actions can be ensured by restricting the action space at maximization, but can lead to sub-optimal solutions among feasible alternatives. In this work, we propose Multi Time-scale Constrained DQN, a novel algorithm restricting the action space directly in the Q-update to learn the optimal Q-function for the constrained MDP and the corresponding safe policy. In addition to single-step constraints referring only to the next action, we introduce a formulation for approximate multi-step constraints under the current target policy based on truncated value-functions to enhance interpretability. We compare our algorithm to reward shaping and Lagrangian methods in the application of high-level decision making in autonomous driving, considering constraints for safety, keeping right and comfort. We train our agent in the open-source simulator SUMO and on the real HighD data set.
Tasks	Autonomous Driving, Decision Making
Published	2020-03-20
URL	https://arxiv.org/abs/2003.09398v1
PDF	https://arxiv.org/pdf/2003.09398v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-multi-time-scale-constraints-in
Repo
Framework

From Statistical Relational to Neuro-Symbolic Artificial Intelligence


Title	From Statistical Relational to Neuro-Symbolic Artificial Intelligence
Authors	Luc De Raedt, Sebastijan Dumančić, Robin Manhaeve, Giuseppe Marra
Abstract	Neuro-symbolic and statistical relational artificial intelligence both integrate frameworks for learning with logical reasoning. This survey identifies several parallels across seven different dimensions between these two fields. These cannot only be used to characterize and position neuro-symbolic artificial intelligence approaches but also to identify a number of directions for further research.
Tasks
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08316v2
PDF	https://arxiv.org/pdf/2003.08316v2.pdf
PWC	https://paperswithcode.com/paper/from-statistical-relational-to-neuro-symbolic
Repo
Framework

A Compact Spectral Descriptor for Shape Deformations


Title	A Compact Spectral Descriptor for Shape Deformations
Authors	Skylar Sible, Rodrigo Iza-Teran, Jochen Garcke, Nikola Aulig, Patricia Wollstadt
Abstract	Modern product design in the engineering domain is increasingly driven by computational analysis including finite-element based simulation, computational optimization, and modern data analysis techniques such as machine learning. To apply these methods, suitable data representations for components under development as well as for related design criteria have to be found. While a component’s geometry is typically represented by a polygon surface mesh, it is often not clear how to parametrize critical design properties in order to enable efficient computational analysis. In the present work, we propose a novel methodology to obtain a parameterization of a component’s plastic deformation behavior under stress, which is an important design criterion in many application domains, for example, when optimizing the crash behavior in the automotive context. Existing parameterizations limit computational analysis to relatively simple deformations and typically require extensive input by an expert, making the design process time intensive and costly. Hence, we propose a way to derive a compact descriptor of deformation behavior that is based on spectral mesh processing and enables a low-dimensional representation of also complex deformations.We demonstrate the descriptor’s ability to represent relevant deformation behavior by applying it in a nearest-neighbor search to identify similar simulation results in a filtering task. The proposed descriptor provides a novel approach to the parametrization of geometric deformation behavior and enables the use of state-of-the-art data analysis techniques such as machine learning to engineering tasks concerned with plastic deformation behavior.
Tasks
Published	2020-03-10
URL	https://arxiv.org/abs/2003.08758v1
PDF	https://arxiv.org/pdf/2003.08758v1.pdf
PWC	https://paperswithcode.com/paper/a-compact-spectral-descriptor-for-shape
Repo
Framework

Analysing Affective Behavior in the First ABAW 2020 Competition


Title	Analysing Affective Behavior in the First ABAW 2020 Competition
Authors	Dimitrios Kollias, Attila Schulc, Elnar Hajiyev, Stefanos Zafeiriou
Abstract	The Affective Behavior Analysis in-the-wild (ABAW) 2020 Competition is the first Competition aiming at automatic analysis of the three main behavior tasks of valence-arousal estimation, basic expression recognition and action unit detection. It is split into three Challenges, each one addressing a respective behavior task. For the Challenges, we provide a common benchmark database, Aff-Wild2, which is a large scale in-the-wild database and the first one annotated for all these three tasks. In this paper, we describe this Competition, to be held in conjunction with the IEEE Conference on Face and Gesture Recognition, May 2020, in Buenos Aires, Argentina. We present the three Challenges, with the utilized Competition corpora. We outline the evaluation metrics and present the baseline methodologies and the obtained results when these are applied to each Challenge. More information regarding the Competition and details for how to access the utilized database, are provided in the Competition site: http://ibug.doc.ic.ac.uk/resources/fg-2020-competition-affective-behavior-analysis.
Tasks	Action Unit Detection, Gesture Recognition
Published	2020-01-30
URL	https://arxiv.org/abs/2001.11409v1
PDF	https://arxiv.org/pdf/2001.11409v1.pdf
PWC	https://paperswithcode.com/paper/analysing-affective-behavior-in-the-first
Repo
Framework

Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve


Title	Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve
Authors	Sen Jia, Neil D. B. Bruce
Abstract	Saliency detection has been widely studied because it plays an important role in various vision applications, but it is difficult to evaluate saliency systems because each measure has its own bias. In this paper, we first revisit the problem of applying the widely used saliency metrics on modern Convolutional Neural Networks(CNNs). Our investigation shows the saliency datasets have been built based on different choices of parameters and CNNs are designed to fit a dataset-specific distribution. Secondly, we show that the Shuffled Area Under Curve(S-AUC) metric still suffers from spatial biases. We propose a new saliency metric based on the AUC property, which aims at sampling a more directional negative set for evaluation, denoted as Farthest-Neighbor AUC(FN-AUC). We also propose a strategy to measure the quality of the sampled negative set. Our experiment shows FN-AUC can measure spatial biases, central and peripheral, more effectively than S-AUC without penalizing the fixation locations. Thirdly, we propose a global smoothing function to overcome the problem of few value degrees (output quantization) in computing AUC metrics. Comparing with random noise, our smooth function can create unique values without losing the relative saliency relationship.
Tasks	Quantization, Saliency Detection
Published	2020-02-24
URL	https://arxiv.org/abs/2002.10540v1
PDF	https://arxiv.org/pdf/2002.10540v1.pdf
PWC	https://paperswithcode.com/paper/revisiting-saliency-metrics-farthest-neighbor
Repo
Framework


Title	DeepStrip: High Resolution Boundary Refinement
Authors	Peng Zhou, Brian Price, Scott Cohen, Gregg Wilensky, Larry S. Davis
Abstract	In this paper, we target refining the boundaries in high resolution images given low resolution masks. For memory and computation efficiency, we propose to convert the regions of interest into strip images and compute a boundary prediction in the strip domain. To detect the target boundary, we present a framework with two prediction layers. First, all potential boundaries are predicted as an initial prediction and then a selection layer is used to pick the target boundary and smooth the result. To encourage accurate prediction, a loss which measures the boundary distance in the strip domain is introduced. In addition, we enforce a matching consistency and C0 continuity regularization to the network to reduce false alarms. Extensive experiments on both public and a newly created high resolution dataset strongly validate our approach.
Tasks
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11670v1
PDF	https://arxiv.org/pdf/2003.11670v1.pdf
PWC	https://paperswithcode.com/paper/deepstrip-high-resolution-boundary-refinement
Repo
Framework

DSSLP: A Distributed Framework for Semi-supervised Link Prediction


Title	DSSLP: A Distributed Framework for Semi-supervised Link Prediction
Authors	Dalong Zhang, Xianzheng Song, Ziqi Liu, Zhiqiang Zhang, Xin Huang, Lin Wang, Jun Zhou
Abstract	Link prediction is widely used in a variety of industrial applications, such as merchant recommendation, fraudulent transaction detection, and so on. However, it’s a great challenge to train and deploy a link prediction model on industrial-scale graphs with billions of nodes and edges. In this work, we present a scalable and distributed framework for semi-supervised link prediction problem (named DSSLP), which is able to handle industrial-scale graphs. Instead of training model on the whole graph, DSSLP is proposed to train on the \emph{$k$-hops neighborhood} of nodes in a mini-batch setting, which helps reduce the scale of the input graph and distribute the training procedure. In order to generate negative examples effectively, DSSLP contains a distributed batched runtime sampling module. It implements uniform and dynamic sampling approaches, and is able to adaptively construct positive and negative examples to guide the training process. Moreover, DSSLP proposes a model-split strategy to accelerate the speed of inference process of the link prediction task. Experimental results demonstrate that the effectiveness and efficiency of DSSLP in serval public datasets as well as real-world datasets of industrial-scale graphs.
Tasks	Link Prediction
Published	2020-02-27
URL	https://arxiv.org/abs/2002.12056v2
PDF	https://arxiv.org/pdf/2002.12056v2.pdf
PWC	https://paperswithcode.com/paper/dsslp-a-distributed-framework-for-semi
Repo
Framework

BasConv: Aggregating Heterogeneous Interactions for Basket Recommendation with Graph Convolutional Neural Network


Title	BasConv: Aggregating Heterogeneous Interactions for Basket Recommendation with Graph Convolutional Neural Network
Authors	Zhiwei Liu, Mengting Wan, Stephen Guo, Kannan Achan, Philip S. Yu
Abstract	Within-basket recommendation reduces the exploration time of users, where the user’s intention of the basket matters. The intent of a shopping basket can be retrieved from both user-item collaborative filtering signals and multi-item correlations. By defining a basket entity to represent the basket intent, we can model this problem as a basket-item link prediction task in the User-Basket-Item~(UBI) graph. Previous work solves the problem by leveraging user-item interactions and item-item interactions simultaneously. However, collectivity and heterogeneity characteristics are hardly investigated before. Collectivity defines the semantics of each node which should be aggregated from both directly and indirectly connected neighbors. Heterogeneity comes from multi-type interactions as well as multi-type nodes in the UBI graph. To this end, we propose a new framework named \textbf{BasConv}, which is based on the graph convolutional neural network. Our BasConv model has three types of aggregators specifically designed for three types of nodes. They collectively learn node embeddings from both neighborhood and high-order context. Additionally, the interactive layers in the aggregators can distinguish different types of interactions. Extensive experiments on two real-world datasets prove the effectiveness of BasConv.
Tasks	Link Prediction
Published	2020-01-14
URL	https://arxiv.org/abs/2001.09900v1
PDF	https://arxiv.org/pdf/2001.09900v1.pdf
PWC	https://paperswithcode.com/paper/basconv-aggregating-heterogeneous
Repo
Framework

PoseNet3D: Unsupervised 3D Human Shape and Pose Estimation


Title	PoseNet3D: Unsupervised 3D Human Shape and Pose Estimation
Authors	Shashank Tripathi, Siddhant Ranade, Ambrish Tyagi, Amit Agrawal
Abstract	Recovering 3D human pose from 2D joints is a highly unconstrained problem. We propose a novel neural network framework, PoseNet3D, that takes 2D joints as input and outputs 3D skeletons and SMPL body model parameters. By casting our learning approach in a student-teacher framework, we avoid using any 3D data such as paired/unpaired 3D data, motion capture sequences, depth images or multi-view images during training. We first train a teacher network that outputs 3D skeletons, using only 2D poses for training. The teacher network distills its knowledge to a student network that predicts 3D pose in SMPL representation. Finally, both the teacher and the student networks are jointly fine-tuned in an end-to-end manner using temporal, self-consistency and adversarial losses, improving the accuracy of each individual network. Results on Human3.6M dataset for 3D human pose estimation demonstrate that our approach reduces the 3D joint prediction error by 18% compared to previous unsupervised methods. Qualitative results on in-the-wild datasets show that the recovered 3D poses and meshes are natural, realistic, and flow smoothly over consecutive frames.
Tasks	3D Human Pose Estimation, Motion Capture, Pose Estimation
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03473v1
PDF	https://arxiv.org/pdf/2003.03473v1.pdf
PWC	https://paperswithcode.com/paper/posenet3d-unsupervised-3d-human-shape-and
Repo
Framework

A large-scale Twitter dataset for drug safety applications mined from publicly existing resources


Title	A large-scale Twitter dataset for drug safety applications mined from publicly existing resources
Authors	Ramya Tekumalla, Juan M. Banda
Abstract	With the increase in popularity of deep learning models for natural language processing (NLP) tasks, in the field of Pharmacovigilance, more specifically for the identification of Adverse Drug Reactions (ADRs), there is an inherent need for large-scale social-media datasets aimed at such tasks. With most researchers allocating large amounts of time to crawl Twitter or buying expensive pre-curated datasets, then manually annotating by humans, these approaches do not scale well as more and more data keeps flowing in Twitter. In this work we re-purpose a publicly available archived dataset of more than 9.4 billion Tweets with the objective of creating a very large dataset of drug usage-related tweets. Using existing manually curated datasets from the literature, we then validate our filtered tweets for relevance using machine learning methods, with the end result of a publicly available dataset of 1,181,993 million tweets for public use. We provide all code and detailed procedure on how to extract this dataset and the selected tweet ids for researchers to use.
Tasks
Published	2020-03-31
URL	https://arxiv.org/abs/2003.13900v1
PDF	https://arxiv.org/pdf/2003.13900v1.pdf
PWC	https://paperswithcode.com/paper/a-large-scale-twitter-dataset-for-drug-safety
Repo
Framework

Towards Neural Machine Translation for Edoid Languages


Title	Towards Neural Machine Translation for Edoid Languages
Authors	Iroro Orife
Abstract	Many Nigerian languages have relinquished their previous prestige and purpose in modern society to English and Nigerian Pidgin. For the millions of L1 speakers of indigenous languages, there are inequalities that manifest themselves as unequal access to information, communications, health care, security as well as attenuated participation in political and civic life. To minimize exclusion and promote socio-linguistic and economic empowerment, this work explores the feasibility of Neural Machine Translation (NMT) for the Edoid language family of Southern Nigeria. Using the new JW300 public dataset, we trained and evaluated baseline translation models for four widely spoken languages in this group: `Ed'o, 'Es'an, Urhobo and Isoko. Trained models, code and datasets have been open-sourced to advance future research efforts on Edoid language technology.
Tasks	Machine Translation
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10704v1
PDF	https://arxiv.org/pdf/2003.10704v1.pdf
PWC	https://paperswithcode.com/paper/towards-neural-machine-translation-for-edoid
Repo
Framework

Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks


Title	Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks
Authors	Robert D. Hawkins, Noah D. Goodman, Adele E. Goldberg, Thomas L. Griffiths
Abstract	A key property of linguistic conventions is that they hold over an entire community of speakers, allowing us to communicate efficiently even with people we have never met before. At the same time, much of our language use is partner-specific: we know that words may be understood differently by different people based on local common ground. This poses a challenge for accounts of convention formation. Exactly how do agents make the inferential leap to community-wide expectations while maintaining partner-specific knowledge? We propose a hierarchical Bayesian model of convention to explain how speakers and listeners abstract away meanings that seem to be shared across partners. To evaluate our model’s predictions, we conducted an experiment where participants played an extended natural-language communication game with different partners in a small community. We examine several measures of generalization across partners, and find key signatures of local adaptation as well as collective convergence. These results suggest that local partner-specific learning is not only compatible with global convention formation but may facilitate it when coupled with a powerful hierarchical inductive mechanism.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01510v1
PDF	https://arxiv.org/pdf/2002.01510v1.pdf
PWC	https://paperswithcode.com/paper/generalizing-meanings-from-partners-to
Repo
Framework