April 2, 2020

3184 words 15 mins read

Paper Group ANR 322

Paper Group ANR 322

Mutual Learning Network for Multi-Source Domain Adaptation. Learning Invariant Representation for Unsupervised Image Restoration. Conversational Structure Aware and Context Sensitive Topic Model for Online Discussions. From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization. REALM: Retrieval-Au …

Mutual Learning Network for Multi-Source Domain Adaptation

Title Mutual Learning Network for Multi-Source Domain Adaptation
Authors Zhenpeng Li, Zhen Zhao, Yuhong Guo, Haifeng Shen, Jieping Ye
Abstract Early Unsupervised Domain Adaptation (UDA) methods have mostly assumed the setting of a single source domain, where all the labeled source data come from the same distribution. However, in practice the labeled data can come from multiple source domains with different distributions. In such scenarios, the single source domain adaptation methods can fail due to the existence of domain shifts across different source domains and multi-source domain adaptation methods need to be designed. In this paper, we propose a novel multi-source domain adaptation method, Mutual Learning Network for Multiple Source Domain Adaptation (ML-MSDA). Under the framework of mutual learning, the proposed method pairs the target domain with each single source domain to train a conditional adversarial domain adaptation network as a branch network, while taking the pair of the combined multi-source domain and target domain to train a conditional adversarial adaptive network as the guidance network. The multiple branch networks are aligned with the guidance network to achieve mutual learning by enforcing JS-divergence regularization over their prediction probability distributions on the corresponding target data. We conduct extensive experiments on multiple multi-source domain adaptation benchmark datasets. The results show the proposed ML-MSDA method outperforms the comparison methods and achieves the state-of-the-art performance.
Tasks Domain Adaptation, Unsupervised Domain Adaptation
Published 2020-03-29
URL https://arxiv.org/abs/2003.12944v1
PDF https://arxiv.org/pdf/2003.12944v1.pdf
PWC https://paperswithcode.com/paper/mutual-learning-network-for-multi-source

Learning Invariant Representation for Unsupervised Image Restoration

Title Learning Invariant Representation for Unsupervised Image Restoration
Authors Wenchao Du, Hu Chen, Hongyu Yang
Abstract Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision. Instead, we propose an unsupervised learning method that explicitly learns invariant presentation from noisy data and reconstructs clear observations. To do so, we introduce discrete disentangling representation and adversarial domain adaption into general domain transfer framework, aided by extra self-supervised modules including background and semantic consistency constraints, learning robust representation under dual domain constraints, such as feature and image domains. Experiments on synthetic and real noise removal tasks show the proposed method achieves comparable performance with other state-of-the-art supervised and unsupervised methods, while having faster and stable convergence than other domain adaption methods.
Tasks Domain Adaptation, Image Restoration
Published 2020-03-28
URL https://arxiv.org/abs/2003.12769v1
PDF https://arxiv.org/pdf/2003.12769v1.pdf
PWC https://paperswithcode.com/paper/learning-invariant-representation-for

Conversational Structure Aware and Context Sensitive Topic Model for Online Discussions

Title Conversational Structure Aware and Context Sensitive Topic Model for Online Discussions
Authors Yingcheng Sun, Kenneth Loparo, Richard Kolacinski
Abstract Millions of online discussions are generated everyday on social media platforms. Topic modelling is an efficient way of better understanding large text datasets at scale. Conventional topic models have had limited success in online discussions, and to overcome their limitations, we use the discussion thread tree structure and propose a “popularity” metric to quantify the number of replies to a comment to extend the frequency of word occurrences, and the “transitivity” concept to characterize topic dependency among nodes in a nested discussion thread. We build a Conversational Structure Aware Topic Model (CSATM) based on popularity and transitivity to infer topics and their assignments to comments. Experiments on real forum datasets are used to demonstrate improved performance for topic extraction with six different measurements of coherence and impressive accuracy for topic assignments.
Tasks Topic Models
Published 2020-02-06
URL https://arxiv.org/abs/2002.02353v1
PDF https://arxiv.org/pdf/2002.02353v1.pdf
PWC https://paperswithcode.com/paper/conversational-structure-aware-and-context

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization

Title From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
Authors Julien Perolat, Remi Munos, Jean-Baptiste Lespiau, Shayegan Omidshafiei, Mark Rowland, Pedro Ortega, Neil Burch, Thomas Anthony, David Balduzzi, Bart De Vylder, Georgios Piliouras, Marc Lanctot, Karl Tuyls
Abstract In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincar'e recurrence from normal-form games to zero-sum two-player imperfect information games and other sequential game settings. We then investigate how adapting the reward (by adding a regularization term) of the game can give strong convergence guarantees in monotone games. We continue by showing how this reward adaptation technique can be leveraged to build algorithms that converge exactly to the Nash equilibrium. Finally, we show how these insights can be directly used to build state-of-the-art model-free algorithms for zero-sum two-player Imperfect Information Games (IIG).
Published 2020-02-19
URL https://arxiv.org/abs/2002.08456v1
PDF https://arxiv.org/pdf/2002.08456v1.pdf
PWC https://paperswithcode.com/paper/from-poincare-recurrence-to-convergence-in

REALM: Retrieval-Augmented Language Model Pre-Training

Title REALM: Retrieval-Augmented Language Model Pre-Training
Authors Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, Ming-Wei Chang
Abstract Language model pre-training has been shown to capture a surprising amount of world knowledge, crucial for NLP tasks such as question answering. However, this knowledge is stored implicitly in the parameters of a neural network, requiring ever-larger networks to cover more facts. To capture knowledge in a more modular and interpretable way, we augment language model pre-training with a latent knowledge retriever, which allows the model to retrieve and attend over documents from a large corpus such as Wikipedia, used during pre-training, fine-tuning and inference. For the first time, we show how to pre-train such a knowledge retriever in an unsupervised manner, using masked language modeling as the learning signal and backpropagating through a retrieval step that considers millions of documents. We demonstrate the effectiveness of Retrieval-Augmented Language Model pre-training (REALM) by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA). We compare against state-of-the-art models for both explicit and implicit knowledge storage on three popular Open-QA benchmarks, and find that we outperform all previous methods by a significant margin (4-16% absolute accuracy), while also providing qualitative benefits such as interpretability and modularity.
Tasks Language Modelling, Open-Domain Question Answering, Question Answering
Published 2020-02-10
URL https://arxiv.org/abs/2002.08909v1
PDF https://arxiv.org/pdf/2002.08909v1.pdf
PWC https://paperswithcode.com/paper/realm-retrieval-augmented-language-model-pre

Multimodal fusion of imaging and genomics for lung cancer recurrence prediction

Title Multimodal fusion of imaging and genomics for lung cancer recurrence prediction
Authors Vaishnavi Subramanian, Minh N. Do, Tanveer Syeda-Mahmood
Abstract Lung cancer has a high rate of recurrence in early-stage patients. Predicting the post-surgical recurrence in lung cancer patients has traditionally been approached using single modality information of genomics or radiology images. We investigate the potential of multimodal fusion for this task. By combining computed tomography (CT) images and genomics, we demonstrate improved prediction of recurrence using linear Cox proportional hazards models with elastic net regularization. We work on a recent non-small cell lung cancer (NSCLC) radiogenomics dataset of 130 patients and observe an increase in concordance-index values of up to 10%. Employing non-linear methods from the neural network literature, such as multi-layer perceptrons and visual-question answering fusion modules, did not improve performance consistently. This indicates the need for larger multimodal datasets and fusion techniques better adapted to this biological setting.
Tasks Computed Tomography (CT), Question Answering, Visual Question Answering
Published 2020-02-05
URL https://arxiv.org/abs/2002.01982v1
PDF https://arxiv.org/pdf/2002.01982v1.pdf
PWC https://paperswithcode.com/paper/multimodal-fusion-of-imaging-and-genomics-for

StickyPillars: Robust feature matching on point clouds using Graph Neural Networks

Title StickyPillars: Robust feature matching on point clouds using Graph Neural Networks
Authors Martin Simon, Kai Fischer, Stefan Milz, Christian Tobias Witt, Horst-Michael Gross
Abstract StickyPillars introduces a sparse feature matching method on point clouds. It is the first approach applying Graph Neural Networks on point clouds to stick points of interest. The feature estimation and assignment relies on the optimal transport problem, where the cost is based on the neural network itself. We utilize a Graph Neural Network for context aggregation with the aid of multihead self and cross attention. In contrast to image based feature matching methods, the architecture learns feature extraction in an end-to-end manner. Hence, the approach does not rely on handcrafted features. Our method outperforms state-of-the art matching algorithms, while providing real-time capability.
Published 2020-02-10
URL https://arxiv.org/abs/2002.03983v1
PDF https://arxiv.org/pdf/2002.03983v1.pdf
PWC https://paperswithcode.com/paper/stickypillars-robust-feature-matching-on

Appearance Fusion of Multiple Cues for Video Co-localization

Title Appearance Fusion of Multiple Cues for Video Co-localization
Authors Koteswar Rao Jerripothula
Abstract This work addresses a problem named video co-localization that aims at localizing the objects in videos jointly. Although there are numerous cues available for this purpose, for example, saliency, motion, and joint, their robust fusion can be quite challenging at times due to their spatial inconsistencies. To overcome this, in this paper, we propose a novel appearance fusion method where we fuse appearance models derived from these cues rather than spatially fusing their maps. In this method, we evaluate the cues in terms of their reliability and consensus to guide the appearance fusion process. We also develop a novel joint cue relying on topological hierarchy. We utilize the final fusion results to produce a few candidate bounding boxes and for subsequent optimal selection among them while considering the spatiotemporal constraints. The proposed method achieves promising results on the YouTube Objects dataset.
Published 2020-03-21
URL https://arxiv.org/abs/2003.09556v1
PDF https://arxiv.org/pdf/2003.09556v1.pdf
PWC https://paperswithcode.com/paper/appearance-fusion-of-multiple-cues-for-video

Uncovering Hidden Semantics of Set Information in Knowledge Bases

Title Uncovering Hidden Semantics of Set Information in Knowledge Bases
Authors Shrestha Ghosh, Simon Razniewski, Gerhard Weikum
Abstract Knowledge Bases (KBs) contain a wealth of structured information about entities and predicates. This paper focuses on set-valued predicates, i.e., the relationship between an entity and a set of entities. In KBs, this information is often represented in two formats: (i) via counting predicates such as numberOfChildren and staffSize, that store aggregated integers, and (ii) via enumerating predicates such as parentOf and worksFor, that store individual set memberships. Both formats are typically complementary: unlike enumerating predicates, counting predicates do not give away individuals, but are more likely informative towards the true set size, thus this coexistence could enable interesting applications in question answering and KB curation. In this paper we aim at uncovering this hidden knowledge. We proceed in two steps. (i) We identify set-valued predicates from a given KB predicates via statistical and embedding-based features. (ii) We link counting predicates and enumerating predicates by a combination of co-occurrence, correlation and textual relatedness metrics. We analyze the prevalence of count information in four prominent knowledge bases, and show that our linking method achieves up to 0.55 F1 score in set predicate identification versus 0.40 F1 score of a random selection, and normalized discounted gains of up to 0.84 at position 1 and 0.75 at position 3 in relevant predicate alignments. Our predicate alignments are showcased in a demonstration system available at https://counqer.mpi-inf.mpg.de/spo.
Tasks Question Answering
Published 2020-03-06
URL https://arxiv.org/abs/2003.03155v2
PDF https://arxiv.org/pdf/2003.03155v2.pdf
PWC https://paperswithcode.com/paper/uncovering-hidden-semantics-of-set

Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner

Title Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner
Authors Yunlu Wang, Menghan Hu, Qingli Li, Xiao-Ping Zhang, Guangtao Zhai, Nan Yao
Abstract Research significance: During the epidemic prevention and control period, our study can be helpful in prognosis, diagnosis and screening for the patients infected with COVID-19 (the novel coronavirus) based on breathing characteristics. According to the latest clinical research, the respiratory pattern of COVID-19 is different from the respiratory patterns of flu and the common cold. One significant symptom that occurs in the COVID-19 is Tachypnea. People infected with COVID-19 have more rapid respiration. Our study can be utilized to distinguish various respiratory patterns and our device can be preliminarily put to practical use. Demo videos of this method working in situations of one subject and two subjects can be downloaded online. Research details: Accurate detection of the unexpected abnormal respiratory pattern of people in a remote and unobtrusive manner has great significance. In this work, we innovatively capitalize on depth camera and deep learning to achieve this goal. The challenges in this task are twofold: the amount of real-world data is not enough for training to get the deep model; and the intra-class variation of different types of respiratory patterns is large and the outer-class variation is small. In this paper, considering the characteristics of actual respiratory signals, a novel and efficient Respiratory Simulation Model (RSM) is first proposed to fill the gap between the large amount of training data and scarce real-world data. Subsequently, we first apply a GRU neural network with bidirectional and attentional mechanisms (BI-AT-GRU) to classify 6 clinically significant respiratory patterns (Eupnea, Tachypnea, Bradypnea, Biots, Cheyne-Stokes and Central-Apnea). The proposed deep model and the modeling ideas have the great potential to be extended to large scale applications such as public places, sleep scenario, and office environment.
Published 2020-02-12
URL https://arxiv.org/abs/2002.05534v1
PDF https://arxiv.org/pdf/2002.05534v1.pdf
PWC https://paperswithcode.com/paper/abnormal-respiratory-patterns-classifier-may

K-bMOM: a robust Lloyd-type clustering algorithm based on bootstrap Median-of-Means

Title K-bMOM: a robust Lloyd-type clustering algorithm based on bootstrap Median-of-Means
Authors Camille Brunet-Saumard, Edouard Genetay, Adrien Saumard
Abstract We propose a new clustering algorithm that is robust to the presence of outliers in the dataset. We perform Lloyd-type iterations with robust estimates of the centroids. More precisely, we build on the idea of median-of-means statistics to estimate the centroids, but allow for replacement while constructing the blocks. We call this methodology the bootstrap median-of-means (bMOM) and prove that if enough blocks are generated through the bootstrap sampling, then it has a better breakdown point for mean estimation than the classical median-of-means (MOM), where the blocks form a partition of the dataset. From a clustering perspective, bMOM enables to take many blocks of a desired size, thus avoiding possible disappearance of clusters in some blocks, a pitfall that can occur for the partition-based generation of blocks of the classical median-of-means. Experiments on simulated datasets show that the proposed approach, called K-bMOM, performs better than existing robust K-means based methods. It is also recommended to the practitionner to use such a robust approach to initialize their clustering algorithm.
Published 2020-02-10
URL https://arxiv.org/abs/2002.03899v1
PDF https://arxiv.org/pdf/2002.03899v1.pdf
PWC https://paperswithcode.com/paper/k-bmom-a-robust-lloyd-type-clustering

R-MADDPG for Partially Observable Environments and Limited Communication

Title R-MADDPG for Partially Observable Environments and Limited Communication
Authors Rose E. Wang, Michael Everett, Jonathan P. How
Abstract There are several real-world tasks that would benefit from applying multiagent reinforcement learning (MARL) algorithms, including the coordination among self-driving cars. The real world has challenging conditions for multiagent learning systems, such as its partial observable and nonstationary nature. Moreover, if agents must share a limited resource (e.g. network bandwidth) they must all learn how to coordinate resource use. This paper introduces a deep recurrent multiagent actor-critic framework (R-MADDPG) for handling multiagent coordination under partial observable set-tings and limited communication. We investigate recurrency effects on performance and communication use of a team of agents. We demonstrate that the resulting framework learns time dependencies for sharing missing observations, handling resource limitations, and developing different communication patterns among agents.
Tasks Self-Driving Cars
Published 2020-02-16
URL https://arxiv.org/abs/2002.06684v2
PDF https://arxiv.org/pdf/2002.06684v2.pdf
PWC https://paperswithcode.com/paper/r-maddpg-for-partially-observable

Arc-Consistency computes the minimal binarised domains of an STP. Use of the result in a TCSP solver, in a TCSP-based job shop scheduler, and in generalising Dijkstra’s one-to-all algorithm

Title Arc-Consistency computes the minimal binarised domains of an STP. Use of the result in a TCSP solver, in a TCSP-based job shop scheduler, and in generalising Dijkstra’s one-to-all algorithm
Authors Amar Isli
Abstract TCSPs (Temporal Constraint Satisfaction Problems), as defined in [Dechter et al., 1991], get rid of unary constraints by binarising them after having added an “origin of the world” variable. The constraints are therefore exclusively binary; additionally, a TCSP verifies the property that it is node-consistent and arc-consistent. Path-consistency, the next higher local consistency, solves the consistency problem of a convex TCSP, referred to in [Dechter et al., 1991] as an STP (Simple Temporal Problem); more than that, the output of path-consistency applied to an n+1-variable STP is a minimal and strongly n+1-consistent STP. Weaker versions of path-consistency, aimed at avoiding what is referred to in [Schwalb and Dechter, 1997] as the “fragmentation problem”, are used as filtering procedures in recursive backtracking algorithms for the consistency problem of a general TCSP. In this work, we look at the constraints between the “origin of the world” variable and the other variables, as the (binarised) domains of these other variables. With this in mind, we define a notion of arc-consistency for TCSPs, which we will refer to as binarised-domains Arc-Consistency, or bdArc-Consistency for short. We provide an algorithm achieving bdArc-Consistency for a TCSP, which we will refer to as bdAC3, for it is an adaptation of Mackworth’s [1977] well-known arc-consistency algorithm AC3. We show that bdArc-Consistency computes the minimal (binarised) domains of an STP. We then show how to use the result in a general TCSP solver, in a TCSP-based job shop scheduler, and in generalising the well-known Dijkstra’s one-to-all shortest paths algorithm.
Published 2020-02-22
URL https://arxiv.org/abs/2002.11508v1
PDF https://arxiv.org/pdf/2002.11508v1.pdf
PWC https://paperswithcode.com/paper/arc-consistency-computes-the-minimal

Triplet Permutation Method for Deep Learning of Single-Shot Person Re-Identification

Title Triplet Permutation Method for Deep Learning of Single-Shot Person Re-Identification
Authors M. J. Gómez-Silva, J. M. Armingol, A. de la Escalera
Abstract Solving Single-Shot Person Re-Identification (Re-Id) by training Deep Convolutional Neural Networks is a daunting challenge, due to the lack of training data, since only two images per person are available. This causes the overfitting of the models, leading to degenerated performance. This paper formulates the Triplet Permutation method to generate multiple training sets, from a certain re-id dataset. This is a novel strategy for feeding triplet networks, which reduces the overfitting of the Single-Shot Re-Id model. The improved performance has been demonstrated over one of the most challenging Re-Id datasets, PRID2011, proving the effectiveness of the method.
Tasks Person Re-Identification
Published 2020-03-18
URL https://arxiv.org/abs/2003.08303v1
PDF https://arxiv.org/pdf/2003.08303v1.pdf
PWC https://paperswithcode.com/paper/triplet-permutation-method-for-deep-learning

The Complexity of Interactively Learning a Stable Matching by Trial and Error

Title The Complexity of Interactively Learning a Stable Matching by Trial and Error
Authors Ehsan Emamjomeh-Zadeh, Yannai A. Gonczarowski, David Kempe
Abstract In a stable matching setting, we consider a query model that allows for an interactive learning algorithm to make precisely one type of query: proposing a matching, the response to which is either that the proposed matching is stable, or a blocking pair (chosen adversarially) indicating that this matching is unstable. For one-to-one matching markets, our main result is an essentially tight upper bound of $O(n^2\log n)$ on the deterministic query complexity of interactively learning a stable matching in this coarse query model, along with an efficient randomized algorithm that achieves this query complexity with high probability. For many-to-many matching markets in which participants have responsive preferences, we first give an interactive learning algorithm whose query complexity and running time are polynomial in the size of the market if the maximum quota of each agent is bounded; our main result for many-to-many markets is that the deterministic query complexity can be made polynomial (more specifically, $O(n^3 \log n)$) in the size of the market even for arbitrary (e.g., linear in the market size) quotas.
Published 2020-02-18
URL https://arxiv.org/abs/2002.07363v1
PDF https://arxiv.org/pdf/2002.07363v1.pdf
PWC https://paperswithcode.com/paper/the-complexity-of-interactively-learning-a
comments powered by Disqus