January 27, 2020

3359 words 16 mins read

Paper Group ANR 1083

Learning to Generalize from Sparse and Underspecified Rewards. Malware Detection Using Dynamic Birthmarks. Deep Learning Algorithms to Isolate and Quantify the Structures of the Anterior Segment in Optical Coherence Tomography Images. Teaching deep neural networks to localize sources in super-resolution microscopy by combining simulation-based lear …

Learning to Generalize from Sparse and Underspecified Rewards


Title	Learning to Generalize from Sparse and Underspecified Rewards
Authors	Rishabh Agarwal, Chen Liang, Dale Schuurmans, Mohammad Norouzi
Abstract	We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. Such success-failure rewards are often underspecified: they do not distinguish between purposeful and accidental success. Generalization from underspecified rewards hinges on discounting spurious trajectories that attain accidental success, while learning from sparse feedback requires effective exploration. We address exploration by using a mode covering direction of KL divergence to collect a diverse set of successful trajectories, followed by a mode seeking KL divergence to train a robust policy. We propose Meta Reward Learning (MeRL) to construct an auxiliary reward function that provides more refined feedback for learning. The parameters of the auxiliary reward function are optimized with respect to the validation performance of a trained policy. The MeRL approach outperforms our alternative reward learning technique based on Bayesian Optimization, and achieves the state-of-the-art on weakly-supervised semantic parsing. It improves previous work by 1.2% and 2.4% on WikiTableQuestions and WikiSQL datasets respectively.
Tasks	Semantic Parsing
Published	2019-02-19
URL	https://arxiv.org/abs/1902.07198v4
PDF	https://arxiv.org/pdf/1902.07198v4.pdf
PWC	https://paperswithcode.com/paper/learning-to-generalize-from-sparse-and
Repo
Framework

Malware Detection Using Dynamic Birthmarks


Title	Malware Detection Using Dynamic Birthmarks
Authors	Swapna Vemparala, Fabio Di Troia, Corrado A. Visaggio, Thomas H. Austin, Mark Stamp
Abstract	In this paper, we explore the effectiveness of dynamic analysis techniques for identifying malware, using Hidden Markov Models (HMMs) and Profile Hidden Markov Models (PHMMs), both trained on sequences of API calls. We contrast our results to static analysis using HMMs trained on sequences of opcodes, and show that dynamic analysis achieves significantly stronger results in many cases. Furthermore, in contrasting our two dynamic analysis techniques, we find that using PHMMs consistently outperforms our analysis based on HMMs.
Tasks	Malware Detection
Published	2019-01-06
URL	http://arxiv.org/abs/1901.07312v1
PDF	http://arxiv.org/pdf/1901.07312v1.pdf
PWC	https://paperswithcode.com/paper/malware-detection-using-dynamic-birthmarks
Repo
Framework

Deep Learning Algorithms to Isolate and Quantify the Structures of the Anterior Segment in Optical Coherence Tomography Images


Title	Deep Learning Algorithms to Isolate and Quantify the Structures of the Anterior Segment in Optical Coherence Tomography Images
Authors	Tan Hung Pham, Sripad Krishna Devalla, Aloysius Ang, Soh Zhi Da, Alexandre H. Thiery, Craig Boote, Ching-Yu Cheng, Victor Koh, Michael J. A. Girard
Abstract	Accurate isolation and quantification of intraocular dimensions in the anterior segment (AS) of the eye using optical coherence tomography (OCT) images is important in the diagnosis and treatment of many eye diseases, especially angle closure glaucoma. In this study, we developed a deep convolutional neural network (DCNN) for the localization of the scleral spur, and the segmentation of anterior segment structures (iris, corneo-sclera shell, anterior chamber). With limited training data, the DCNN was able to detect the scleral spur on unseen ASOCT images as accurately as an experienced ophthalmologist; and simultaneously isolated the anterior segment structures with a Dice coefficient of 95.7%. We then automatically extracted eight clinically relevant ASOCT parameters and proposed an automated quality check process that asserts the reliability of these parameters. When combined with an OCT machine capable of imaging multiple radial sections, the algorithms can provide a more complete objective assessment. This is an essential step toward providing a robust automated framework for reliable quantification of ASOCT scans, for applications in the diagnosis and management of angle closure glaucoma.
Tasks
Published	2019-09-01
URL	https://arxiv.org/abs/1909.00331v1
PDF	https://arxiv.org/pdf/1909.00331v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-algorithms-to-isolate-and
Repo
Framework

Teaching deep neural networks to localize sources in super-resolution microscopy by combining simulation-based learning and unsupervised learning


Title	Teaching deep neural networks to localize sources in super-resolution microscopy by combining simulation-based learning and unsupervised learning
Authors	Artur Speiser, Srinivas C. Turaga, Jakob H. Macke
Abstract	Single-molecule localization microscopy constructs super-resolution images by the sequential imaging and computational localization of sparsely activated fluorophores. Accurate and efficient fluorophore localization algorithms are key to the success of this computational microscopy method. We present a novel localization algorithm based on deep learning which significantly improves upon the state of the art. Our contributions are a novel network architecture for simultaneous detection and localization, and a new training algorithm which enables this deep network to solve the Bayesian inverse problem of detecting and localizing single molecules. Our network architecture uses temporal context from multiple sequentially imaged frames to detect and localize molecules. Our training algorithm combines simulation-based supervised learning with autoencoder-based unsupervised learning to make it more robust against mismatch in the generative model. We demonstrate the performance of our method on datasets imaged using a variety of point spread functions and fluorophore densities. While existing localization algorithms can achieve optimal localization accuracy in data with low fluorophore density, they are confounded by high densities. Our method significantly outperforms the state of the art at high densities and thus, enables faster imaging than previous approaches. Our work also more generally shows how to train deep networks to solve challenging Bayesian inverse problems in biology and physics.
Tasks	Super-Resolution
Published	2019-06-27
URL	https://arxiv.org/abs/1907.00770v1
PDF	https://arxiv.org/pdf/1907.00770v1.pdf
PWC	https://paperswithcode.com/paper/teaching-deep-neural-networks-to-localize
Repo
Framework

Learning Multimodal Fixed-Point Weights using Gradient Descent


Title	Learning Multimodal Fixed-Point Weights using Gradient Descent
Authors	Lukas Enderich, Fabian Timm, Lars Rosenbaum, Wolfram Burgard
Abstract	Due to their high computational complexity, deep neural networks are still limited to powerful processing units. To promote a reduced model complexity by dint of low-bit fixed-point quantization, we propose a gradient-based optimization strategy to generate a symmetric mixture of Gaussian modes (SGM) where each mode belongs to a particular quantization stage. We achieve 2-bit state-of-the-art performance and illustrate the model’s ability for self-dependent weight adaptation during training.
Tasks	Quantization
Published	2019-07-16
URL	https://arxiv.org/abs/1907.07220v1
PDF	https://arxiv.org/pdf/1907.07220v1.pdf
PWC	https://paperswithcode.com/paper/learning-multimodal-fixed-point-weights-using
Repo
Framework

Contextual Grounding of Natural Language Entities in Images


Title	Contextual Grounding of Natural Language Entities in Images
Authors	Farley Lai, Ning Xie, Derek Doran, Asim Kadav
Abstract	In this paper, we introduce a contextual grounding approach that captures the context in corresponding text entities and image regions to improve the grounding accuracy. Specifically, the proposed architecture accepts pre-trained text token embeddings and image object features from an off-the-shelf object detector as input. Additional encoding to capture the positional and spatial information can be added to enhance the feature quality. There are separate text and image branches facilitating respective architectural refinements for different modalities. The text branch is pre-trained on a large-scale masked language modeling task while the image branch is trained from scratch. Next, the model learns the contextual representations of the text tokens and image objects through layers of high-order interaction respectively. The final grounding head ranks the correspondence between the textual and visual representations through cross-modal interaction. In the evaluation, we show that our model achieves the state-of-the-art grounding accuracy of 71.36% over the Flickr30K Entities dataset. No additional pre-training is necessary to deliver competitive results compared with related work that often requires task-agnostic and task-specific pre-training on cross-modal dadasets. The implementation is publicly available at https://gitlab.com/necla-ml/grounding.
Tasks	Language Modelling
Published	2019-11-05
URL	https://arxiv.org/abs/1911.02133v1
PDF	https://arxiv.org/pdf/1911.02133v1.pdf
PWC	https://paperswithcode.com/paper/contextual-grounding-of-natural-language
Repo
Framework

Counterfactual thinking in cooperation dynamics


Title	Counterfactual thinking in cooperation dynamics
Authors	Luis Moniz Pereira, Francisco C. Santos
Abstract	Counterfactual Thinking is a human cognitive ability studied in a wide variety of domains. It captures the process of reasoning about a past event that did not occur, namely what would have happened had this event occurred, or, otherwise, to reason about an event that did occur but what would ensue had it not. Given the wide cognitive empowerment of counterfactual reasoning in the human individual, the question arises of how the presence of individuals with this capability may improve cooperation in populations of self-regarding individuals. Here we propose a mathematical model, grounded on Evolutionary Game Theory, to examine the population dynamics emerging from the interplay between counterfactual thinking and social learning (i.e., individuals that learn from the actions and success of others) whenever the individuals in the population face a collective dilemma. Our results suggest that counterfactual reasoning fosters coordination in collective action problems occurring in large populations, and has a limited impact on cooperation dilemmas in which coordination is not required. Moreover, we show that a small prevalence of individuals resorting to counterfactual thinking is enough to nudge an entire population towards highly cooperative standards.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08946v1
PDF	https://arxiv.org/pdf/1912.08946v1.pdf
PWC	https://paperswithcode.com/paper/counterfactual-thinking-in-cooperation
Repo
Framework

Rapid Visual Categorization is not Guided by Early Salience-Based Selection


Title	Rapid Visual Categorization is not Guided by Early Salience-Based Selection
Authors	John K. Tsotsos, Iuliia Kotseruba, Calden Wloka
Abstract	The current dominant visual processing paradigm in both human and machine research is the feedforward, layered hierarchy of neural-like processing elements. Within this paradigm, visual saliency is seen by many to have a specific role, namely that of early selection. Early selection is thought to enable very fast visual performance by limiting processing to only the most salient candidate portions of an image. This strategy has led to a plethora of saliency algorithms that have indeed improved processing time efficiency in machine algorithms, which in turn have strengthened the suggestion that human vision also employs a similar early selection strategy. However, at least one set of critical tests of this idea has never been performed with respect to the role of early selection in human vision. How would the best of the current saliency models perform on the stimuli used by experimentalists who first provided evidence for this visual processing paradigm? Would the algorithms really provide correct candidate sub-images to enable fast categorization on those same images? Do humans really need this early selection for their impressive performance? Here, we report on a new series of tests of these questions whose results suggest that it is quite unlikely that such an early selection process has any role in human rapid visual categorization.
Tasks
Published	2019-01-15
URL	https://arxiv.org/abs/1901.04908v3
PDF	https://arxiv.org/pdf/1901.04908v3.pdf
PWC	https://paperswithcode.com/paper/early-salient-region-selection-does-not-drive
Repo
Framework

SAT Solvers and Computer Algebra Systems: A Powerful Combination for Mathematics


Title	SAT Solvers and Computer Algebra Systems: A Powerful Combination for Mathematics
Authors	Curtis Bright, Ilias Kotsireas, Vijay Ganesh
Abstract	Over the last few decades, many distinct lines of research aimed at automating mathematics have been developed, including computer algebra systems (CASs) for mathematical modelling, automated theorem provers for first-order logic, SAT/SMT solvers aimed at program verification, and higher-order proof assistants for checking mathematical proofs. More recently, some of these lines of research have started to converge in complementary ways. One success story is the combination of SAT solvers and CASs (SAT+CAS) aimed at resolving mathematical conjectures. Many conjectures in pure and applied mathematics are not amenable to traditional proof methods. Instead, they are best addressed via computational methods that involve very large combinatorial search spaces. SAT solvers are powerful methods to search through such large combinatorial spaces—consequently, many problems from a variety of mathematical domains have been reduced to SAT in an attempt to resolve them. However, solvers traditionally lack deep repositories of mathematical domain knowledge that can be crucial to pruning such large search spaces. By contrast, CASs are deep repositories of mathematical knowledge but lack efficient general search capabilities. By combining the search power of SAT with the deep mathematical knowledge in CASs we can solve many problems in mathematics that no other known methods seem capable of solving. We demonstrate the success of the SAT+CAS paradigm by highlighting many conjectures that have been disproven, verified, or partially verified using our tool MathCheck. These successes indicate that the paradigm is positioned to become a standard method for solving problems requiring both a significant amount of search and deep mathematical reasoning. For example, the SAT+CAS paradigm has recently been used by Heule, Kauers, and Seidl to find many new algorithms for $3\times3$ matrix multiplication.
Tasks	Mathematical Proofs
Published	2019-07-09
URL	https://arxiv.org/abs/1907.04408v2
PDF	https://arxiv.org/pdf/1907.04408v2.pdf
PWC	https://paperswithcode.com/paper/sat-solvers-and-computer-algebra-systems-a
Repo
Framework

α-Rank: Multi-Agent Evaluation by Evolution


Title	α-Rank: Multi-Agent Evaluation by Evolution
Authors	Shayegan Omidshafiei, Christos Papadimitriou, Georgios Piliouras, Karl Tuyls, Mark Rowland, Jean-Baptiste Lespiau, Wojciech M. Czarnecki, Marc Lanctot, Julien Perolat, Remi Munos
Abstract	We introduce {\alpha}-Rank, a principled evolutionary dynamics methodology, for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamical game-theoretic solution concept called Markov-Conley chains (MCCs). The approach leverages continuous-time and discrete-time evolutionary dynamical systems applied to empirical games, and scales tractably in the number of agents, in the type of interactions (beyond dyadic), and the type of empirical games (symmetric and asymmetric). Current models are fundamentally limited in one or more of these dimensions, and are not guaranteed to converge to the desired game-theoretic solution concept (typically the Nash equilibrium). {\alpha}-Rank automatically provides a ranking over the set of agents under evaluation and provides insights into their strengths, weaknesses, and long-term dynamics in terms of basins of attraction and sink components. This is a direct consequence of our new model’s direct correspondence to the dynamical MCC solution concept when its ranking-intensity parameter, {\alpha}, is chosen to be large, which exactly forms the basis of {\alpha}-Rank. In contrast to the Nash equilibrium, which is a static solution concept based solely on fixed points, MCCs are a dynamical solution concept based on the Markov chain formalism, Conley’s Fundamental Theorem of Dynamical Systems, and the core ingredients of dynamical systems: fixed points, recurrent sets, periodic orbits, and limit cycles. Our {\alpha}-Rank method runs in polynomial time with respect to the total number of pure strategy profiles, whereas computing a Nash equilibrium for a general-sum game is known to be intractable. We introduce mathematical proofs that reveal the formal underpinnings of the {\alpha}-Rank methodology. We illustrate the method in canonical games and in AlphaGo, AlphaZero, MuJoCo Soccer, and Poker.
Tasks	Mathematical Proofs
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01373v1
PDF	http://arxiv.org/pdf/1903.01373v1.pdf
PWC	https://paperswithcode.com/paper/-rank-multi-agent-evaluation-by-evolution
Repo
Framework

Quantum-enhanced least-square support vector machine: simplified quantum algorithm and sparse solutions


Title	Quantum-enhanced least-square support vector machine: simplified quantum algorithm and sparse solutions
Authors	Jie Lin, Dan-Bo Zhang, Shuo Zhang, Xiang Wang, Tan Li, Wan-su Bao
Abstract	Quantum algorithms can enhance machine learning in different aspects. Here, we study quantum-enhanced least-square support vector machine (LS-SVM). Firstly, a novel quantum algorithm that uses continuous variable to assist matrix inversion is introduced to simplify the algorithm for quantum LS-SVM, while retaining exponential speed-up. Secondly, we propose a hybrid quantum-classical version for sparse solutions of LS-SVM. By encoding a large dataset into a quantum state, a much smaller transformed dataset can be extracted using quantum matrix toolbox, which is further processed in classical SVM. We also incorporate kernel methods into the above quantum algorithms, which uses both exponential growth Hilbert space of qubits and infinite dimensionality of continuous variable for quantum feature maps. The quantum LS-SVM exploits quantum properties to explore important themes for SVM such as sparsity and kernel methods, and stresses its quantum advantages ranging from speed-up to the potential capacity to solve classically difficult machine learning tasks.
Tasks
Published	2019-08-05
URL	https://arxiv.org/abs/1908.01462v1
PDF	https://arxiv.org/pdf/1908.01462v1.pdf
PWC	https://paperswithcode.com/paper/quantum-enhanced-least-square-support-vector
Repo
Framework

Ontology-Aware Clinical Abstractive Summarization


Title	Ontology-Aware Clinical Abstractive Summarization
Authors	Sean MacAvaney, Sajad Sotudeh, Arman Cohan, Nazli Goharian, Ish Talati, Ross W. Filice
Abstract	Automatically generating accurate summaries from clinical reports could save a clinician’s time, improve summary coverage, and reduce errors. We propose a sequence-to-sequence abstractive summarization model augmented with domain-specific ontological information to enhance content selection and summary generation. We apply our method to a dataset of radiology reports and show that it significantly outperforms the current state-of-the-art on this task in terms of rouge scores. Extensive human evaluation conducted by a radiologist further indicates that this approach yields summaries that are less likely to omit important details, without sacrificing readability or accuracy.
Tasks	Abstractive Text Summarization
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05818v1
PDF	https://arxiv.org/pdf/1905.05818v1.pdf
PWC	https://paperswithcode.com/paper/ontology-aware-clinical-abstractive
Repo
Framework

Cascading Machine Learning to Attack Bitcoin Anonymity


Title	Cascading Machine Learning to Attack Bitcoin Anonymity
Authors	Francesco Zola, Maria Eguimendia, Jan Lukas Bruse, Raul Orduna Urrutia
Abstract	Bitcoin is a decentralized, pseudonymous cryptocurrency that is one of the most used digital assets to date. Its unregulated nature and inherent anonymity of users have led to a dramatic increase in its use for illicit activities. This calls for the development of novel methods capable of characterizing different entities in the Bitcoin network. In this paper, a method to attack Bitcoin anonymity is presented, leveraging a novel cascading machine learning approach that requires only a few features directly extracted from Bitcoin blockchain data. Cascading, used to enrich entities information with data from previous classifications, led to considerably improved multi-class classification performance with excellent values of Precision close to 1.0 for each considered class. Final models were implemented and compared using different machine learning models and showed significantly higher accuracy compared to their baseline implementation. Our approach can contribute to the development of effective tools for Bitcoin entity characterization, which may assist in uncovering illegal activities.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06560v1
PDF	https://arxiv.org/pdf/1910.06560v1.pdf
PWC	https://paperswithcode.com/paper/cascading-machine-learning-to-attack-bitcoin
Repo
Framework

Real-time Attention Based Look-alike Model for Recommender System


Title	Real-time Attention Based Look-alike Model for Recommender System
Authors	Yudan Liu, Kaikai Ge, Xu Zhang, Leyu Lin
Abstract	Recently, deep learning models play more and more important roles in contents recommender systems. However, although the performance of recommendations is greatly improved, the “Matthew effect” becomes increasingly evident. While the head contents get more and more popular, many competitive long-tail contents are difficult to achieve timely exposure because of lacking behavior features. This issue has badly impacted the quality and diversity of recommendations. To solve this problem, look-alike algorithm is a good choice to extend audience for high quality long-tail contents. But the traditional look-alike models which widely used in online advertising are not suitable for recommender systems because of the strict requirement of both real-time and effectiveness. This paper introduces a real-time attention based look-alike model (RALM) for recommender systems, which tackles the challenge of conflict between real-time and effectiveness. RALM realizes real-time look-alike audience extension benefiting from seeds-to-user similarity prediction and improves the effectiveness through optimizing user representation learning and look-alike learning modeling. For user representation learning, we propose a novel neural network structure named attention merge layer to replace the concatenation layer, which significantly improves the expressive ability of multi-fields feature learning. On the other hand, considering the various members of seeds, we design global attention unit and local attention unit to learn robust and adaptive seeds representation with respect to a certain target user. At last, we introduce seeds clustering mechanism which not only reduces the time complexity of attention units prediction but also minimizes the loss of seeds information at the same time. According to our experiments, RALM shows superior effectiveness and performance than popular look-alike models.
Tasks	Recommendation Systems, Representation Learning
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05022v1
PDF	https://arxiv.org/pdf/1906.05022v1.pdf
PWC	https://paperswithcode.com/paper/real-time-attention-based-look-alike-model
Repo
Framework

Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings


Title	Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddings
Authors	Michael Wray, Diane Larlus, Gabriela Csurka, Dima Damen
Abstract	We address the problem of cross-modal fine-grained action retrieval between text and video. Cross-modal retrieval is commonly achieved through learning a shared embedding space, that can indifferently embed modalities. In this paper, we propose to enrich the embedding by disentangling parts-of-speech (PoS) in the accompanying captions. We build a separate multi-modal embedding space for each PoS tag. The outputs of multiple PoS embeddings are then used as input to an integrated multi-modal space, where we perform action retrieval. All embeddings are trained jointly through a combination of PoS-aware and PoS-agnostic losses. Our proposal enables learning specialised embedding spaces that offer multiple views of the same embedded entities. We report the first retrieval results on fine-grained actions for the large-scale EPIC dataset, in a generalised zero-shot setting. Results show the advantage of our approach for both video-to-text and text-to-video action retrieval. We also demonstrate the benefit of disentangling the PoS for the generic task of cross-modal video retrieval on the MSR-VTT dataset.
Tasks	Cross-Modal Retrieval, Video Retrieval
Published	2019-08-09
URL	https://arxiv.org/abs/1908.03477v1
PDF	https://arxiv.org/pdf/1908.03477v1.pdf
PWC	https://paperswithcode.com/paper/fine-grained-action-retrieval-through
Repo
Framework