April 3, 2020

3306 words 16 mins read

Paper Group ANR 51

Paper Group ANR 51

Motivic clustering schemes for directed graphs. Shallow2Deep: Indoor Scene Modeling by Single Image Understanding. The Two Regimes of Deep Network Training. Automated Configuration of Negotiation Strategies. Disrupting Resilient Criminal Networks through Data Analysis: The case of Sicilian Mafia. Theory inspired deep network for instantaneous-frequ …

Motivic clustering schemes for directed graphs

Title Motivic clustering schemes for directed graphs
Authors Facundo Mémoli, Guilherme Vituri F. Pinto
Abstract Motivated by the concept of network motifs we construct certain clustering methods (functors) which are parametrized by a given collection of motifs (or representers).
Published 2020-01-01
URL https://arxiv.org/abs/2001.00278v2
PDF https://arxiv.org/pdf/2001.00278v2.pdf
PWC https://paperswithcode.com/paper/motivic-clustering-schemes-for-directed

Shallow2Deep: Indoor Scene Modeling by Single Image Understanding

Title Shallow2Deep: Indoor Scene Modeling by Single Image Understanding
Authors Yinyu Nie, Shihui Guo, Jian Chang, Xiaoguang Han, Jiahui Huang, Shi-Min Hu, Jian Jun Zhang
Abstract Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a single RGB image, our method simultaneously recovers semantic contents, 3D geometry and object relationship by reasoning indoor environment context. Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling. It involves multi-level convolutional networks to parse indoor semantics/geometry into non-relational and relational knowledge. Non-relational knowledge extracted from shallow-end networks (e.g. room layout, object geometry) is fed forward into deeper levels to parse relational semantics (e.g. support relationship). A Relation Network is proposed to infer the support relationship between objects. All the structured semantics and geometry above are assembled to guide a global optimization for 3D scene modeling. Qualitative and quantitative analysis demonstrates the feasibility of our method in understanding and modeling semantics-enriched indoor scenes by evaluating the performance of reconstruction accuracy, computation performance and scene complexity.
Tasks Scene Understanding
Published 2020-02-22
URL https://arxiv.org/abs/2002.09790v1
PDF https://arxiv.org/pdf/2002.09790v1.pdf
PWC https://paperswithcode.com/paper/shallow2deep-indoor-scene-modeling-by-single

The Two Regimes of Deep Network Training

Title The Two Regimes of Deep Network Training
Authors Guillaume Leclerc, Aleksander Madry
Abstract Learning rate schedule has a major impact on the performance of deep learning models. Still, the choice of a schedule is often heuristical. We aim to develop a precise understanding of the effects of different learning rate schedules and the appropriate way to select them. To this end, we isolate two distinct phases of training, the first, which we refer to as the “large-step” regime, exhibits a rather poor performance from an optimization point of view but is the primary contributor to model generalization; the latter, “small-step” regime exhibits much more “convex-like” optimization behavior but used in isolation produces models that generalize poorly. We find that by treating these regimes separately-and em specializing our training algorithm to each one of them, we can significantly simplify learning rate schedules.
Published 2020-02-24
URL https://arxiv.org/abs/2002.10376v1
PDF https://arxiv.org/pdf/2002.10376v1.pdf
PWC https://paperswithcode.com/paper/the-two-regimes-of-deep-network-training

Automated Configuration of Negotiation Strategies

Title Automated Configuration of Negotiation Strategies
Authors Bram M. Renting, Holger H. Hoos, Catholijn M. Jonker
Abstract Bidding and acceptance strategies have a substantial impact on the outcome of negotiations in scenarios with linear additive and nonlinear utility functions. Over the years, it has become clear that there is no single best strategy for all negotiation settings, yet many fixed strategies are still being developed. We envision a shift in the strategy design question from: What is a good strategy?, towards: What could be a good strategy? For this purpose, we developed a method leveraging automated algorithm configuration to find the best strategies for a specific set of negotiation settings. By empowering automated negotiating agents using automated algorithm configuration, we obtain a flexible negotiation agent that can be configured automatically for a rich space of opponents and negotiation scenarios. To critically assess our approach, the agent was tested in an ANAC-like bilateral automated negotiation tournament setting against past competitors. We show that our automatically configured agent outperforms all other agents, with a 5.1% increase in negotiation payoff compared to the next-best agent. We note that without our agent in the tournament, the top-ranked agent wins by a margin of only 0.01%.
Published 2020-03-31
URL https://arxiv.org/abs/2004.00094v1
PDF https://arxiv.org/pdf/2004.00094v1.pdf
PWC https://paperswithcode.com/paper/automated-configuration-of-negotiation

Disrupting Resilient Criminal Networks through Data Analysis: The case of Sicilian Mafia

Title Disrupting Resilient Criminal Networks through Data Analysis: The case of Sicilian Mafia
Authors Lucia Cavallaro, Annamaria Ficara, Pasquale De Meo, Giacomo Fiumara, Salvatore Catanese, Ovidiu Bagdasar, Antonio Liotta
Abstract Compared to other types of social networks, criminal networks present hard challenges, due to their strong resilience to disruption, which poses severe hurdles to law-enforcement agencies. Herein, we borrow methods and tools from Social Network Analysis to (i) unveil the structure of Sicilian Mafia gangs, based on two real-world datasets, and (ii) gain insights as to how to efficiently disrupt them. Mafia networks have peculiar features, due to the links distribution and strength, which makes them very different from other social networks, and extremely robust to exogenous perturbations. Analysts are also faced with the difficulty in collecting reliable datasets that accurately describe the gangs’ internal structure and their relationships with the external world, which is why earlier studies are largely qualitative, elusive and incomplete. An added value of our work is the generation of two real-world datasets, based on raw data derived from juridical acts, relating to a Mafia organization that operated in Sicily during the first decade of 2000s. We created two different networks, capturing phone calls and physical meetings, respectively. Our network disruption analysis simulated different intervention procedures: (i) arresting one criminal at a time (sequential node removal); and (ii) police raids (node block removal). We measured the effectiveness of each approach through a number of network centrality metrics. We found Betweeness Centrality to be the most effective metric, showing how, by neutralizing only the 5% of the affiliates, network connectivity dropped by 70%. We also identified that, due the peculiar type of interactions in criminal networks (namely, the distribution of the interactions frequency) no significant differences exist between weighted and unweighted network analysis. Our work has significant practical applications for tackling criminal and terrorist networks.
Published 2020-03-10
URL https://arxiv.org/abs/2003.05303v1
PDF https://arxiv.org/pdf/2003.05303v1.pdf
PWC https://paperswithcode.com/paper/disrupting-resilient-criminal-networks

Theory inspired deep network for instantaneous-frequency extraction and signal components recovery from discrete blind-source data

Title Theory inspired deep network for instantaneous-frequency extraction and signal components recovery from discrete blind-source data
Authors Charles K. Chui, Ningning Han, Hrushikesh N. Mhaskar
Abstract This paper is concerned with the inverse problem of recovering the unknown signal components, along with extraction of their instantaneous frequencies (IFs), governed by the adaptive harmonic model (AHM), from discrete (and possibly non-uniform) samples of the blind-source composite signal. None of the existing decomposition methods and algorithms, including the most popular empirical mode decomposition (EMD) computational scheme and its current modifications, is capable of solving this inverse problem. In order to meet the AHM formulation and to extract the IFs of the decomposed components, called intrinsic mode functions (IMFs), each IMF of EMD is extended to an analytic function in the upper half of the complex plane via the Hilbert transform, followed by taking the real part of the polar form of the analytic extension. Unfortunately, this approach most often fails to resolve the inverse problem satisfactorily. More recently, to resolve the inverse problem, the notion of synchrosqueezed wavelet transform (SST) was proposed by Daubechies and Maes, and further developed in many other papers, while a more direct method, called signal separation operation (SSO), was proposed and developed in our previous work published in the journal, Applied and Computational Harmonic Analysis, vol. 30(2):243-261, 2016. In the present paper, we propose a synthesis of SSO using a deep neural network, based directly on a discrete sample set, that may be non-uniformly sampled, of the blind-source signal. Our method is localized, as illustrated by a number of numerical examples, including components with different signal arrival and departure times. It also yields short-term prediction of the signal components, along with their IFs. Our neural networks are inspired by theory, designed so that they do not require any training in the traditional sense.
Published 2020-01-31
URL https://arxiv.org/abs/2001.12006v1
PDF https://arxiv.org/pdf/2001.12006v1.pdf
PWC https://paperswithcode.com/paper/theory-inspired-deep-network-for

UFTR: A Unified Framework for Ticket Routing

Title UFTR: A Unified Framework for Ticket Routing
Authors Jianglei Han, Jing Li, Aixin Sun
Abstract Corporations today face increasing demands for the timely and effective delivery of customer service. This creates the need for a robust and accurate automated solution to what is formally known as the ticket routing problem. This task is to match each unresolved service incident, or “ticket”, to the right group of service experts. Existing studies divide the task into two independent subproblems - initial group assignment and inter-group transfer. However, our study addresses both subproblems jointly using an end-to-end modeling approach. We first performed a preliminary analysis of half a million archived tickets to uncover relevant features. Then, we devised the UFTR, a Unified Framework for Ticket Routing using four types of features (derived from tickets, groups, and their interactions). In our experiments, we implemented two ranking models with the UFTR. Our models outperform baselines on three routing metrics. Furthermore, a post-hoc analysis reveals that this superior performance can largely be attributed to the features that capture the associations between ticket assignment and group assignment. In short, our results demonstrate that the UFTR is a superior solution to the ticket routing problem because it takes into account previously unexploited interrelationships between the group assignment and group transfer problems.
Published 2020-03-02
URL https://arxiv.org/abs/2003.00703v1
PDF https://arxiv.org/pdf/2003.00703v1.pdf
PWC https://paperswithcode.com/paper/uftr-a-unified-framework-for-ticket-routing

Which way? Direction-Aware Attributed Graph Embedding

Title Which way? Direction-Aware Attributed Graph Embedding
Authors Zekarias T. Kefato, Nasrullah Sheikh, Alberto Montresor
Abstract Graph embedding algorithms are used to efficiently represent (encode) a graph in a low-dimensional continuous vector space that preserves the most important properties of the graph. One aspect that is often overlooked is whether the graph is directed or not. Most studies ignore the directionality, so as to learn high-quality representations optimized for node classification. On the other hand, studies that capture directionality are usually effective on link prediction but do not perform well on other tasks. This preliminary study presents a novel text-enriched, direction-aware algorithm called DIAGRAM , based on a carefully designed multi-objective model to learn embeddings that preserve the direction of edges, textual features and graph context of nodes. As a result, our algorithm does not have to trade one property for another and jointly learns high-quality representations for multiple network analysis tasks. We empirically show that DIAGRAM significantly outperforms six state-of-the-art baselines, both direction-aware and oblivious ones,on link prediction and network reconstruction experiments using two popular datasets. It also achieves a comparable performance on node classification experiments against these baselines using the same datasets.
Tasks Graph Embedding, Link Prediction, Node Classification
Published 2020-01-30
URL https://arxiv.org/abs/2001.11297v1
PDF https://arxiv.org/pdf/2001.11297v1.pdf
PWC https://paperswithcode.com/paper/which-way-direction-aware-attributed-graph

Efficient Gaussian Process Bandits by Believing only Informative Actions

Title Efficient Gaussian Process Bandits by Believing only Informative Actions
Authors Amrit Singh Bedi, Dheeraj Peddireddy, Vaneet Aggarwal, Alec Koppel
Abstract Bayesian optimization is a framework for global search via maximum a posteriori updates rather than simulated annealing, and has gained prominence for decision-making under uncertainty. In this work, we cast Bayesian optimization as a multi-armed bandit problem, where the payoff function is sampled from a Gaussian process (GP). Further, we focus on action selections via upper confidence bound (UCB) or expected improvement (EI) due to their prevalent use in practice. Prior works using GPs for bandits cannot allow the iteration horizon $T$ to be large, as the complexity of computing the posterior parameters scales cubically with the number of past observations. To circumvent this computational burden, we propose a simple statistical test: only incorporate an action into the GP posterior when its conditional entropy exceeds an $\epsilon$ threshold. Doing so permits us to derive sublinear regret bounds of GP bandit algorithms up to factors depending on the compression parameter $\epsilon$ for both discrete and continuous action sets. Moreover, the complexity of the GP posterior remains provably finite. Experimentally, we observe state of the art accuracy and complexity tradeoffs for GP bandit algorithms applied to global optimization, suggesting the merits of compressed GPs in bandit settings.
Tasks Decision Making, Decision Making Under Uncertainty
Published 2020-03-23
URL https://arxiv.org/abs/2003.10550v1
PDF https://arxiv.org/pdf/2003.10550v1.pdf
PWC https://paperswithcode.com/paper/efficient-gaussian-process-bandits-by

A Visual Communication Map for Multi-Agent Deep Reinforcement Learning

Title A Visual Communication Map for Multi-Agent Deep Reinforcement Learning
Authors Ngoc Duy Nguyen, Thanh Thi Nguyen, Saeid Nahavandi
Abstract Multi-agent learning distinctly poses significant challenges in the effort to allocate a concealed communication medium. Agents receive thorough knowledge from the medium to determine subsequent actions in a distributed nature. Apparently, the goal is to leverage the cooperation of multiple agents to achieve a designated objective efficiently. Recent studies typically combine a specialized neural network with reinforcement learning to enable communication between agents. This approach, however, limits the number of agents or necessitates the homogeneity of the system. In this paper, we have proposed a more scalable approach that not only deals with a great number of agents but also enables collaboration between dissimilar functional agents and compatibly combined with any deep reinforcement learning methods. Specifically, we create a global communication map to represent the status of each agent in the system visually. The visual map and the environmental state are fed to a shared-parameter network to train multiple agents concurrently. Finally, we select the Asynchronous Advantage Actor-Critic (A3C) algorithm to demonstrate our proposed scheme, namely Visual communication map for Multi-agent A3C (VMA3C). Simulation results show that the use of visual communication map improves the performance of A3C regarding learning speed, reward achievement, and robustness in multi-agent problems.
Published 2020-02-27
URL https://arxiv.org/abs/2002.11882v1
PDF https://arxiv.org/pdf/2002.11882v1.pdf
PWC https://paperswithcode.com/paper/a-visual-communication-map-for-multi-agent

GraphTTS: graph-to-sequence modelling in neural text-to-speech

Title GraphTTS: graph-to-sequence modelling in neural text-to-speech
Authors Aolan Sun, Jianzong Wang, Ning Cheng, Huayi Peng, Zhen Zeng, Jing Xiao
Abstract This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms. The graphical inputs consist of node and edge representations constructed from input texts. The encoding of these graphical inputs incorporates syntax information by a GNN encoder module. Besides, applying the encoder of GraphTTS as a graph auxiliary encoder (GAE) can analyse prosody information from the semantic structure of texts. This can remove the manual selection of reference audios process and makes prosody modelling an end-to-end procedure. Experimental analysis shows that GraphTTS outperforms the state-of-the-art sequence-to-sequence models by 0.24 in Mean Opinion Score (MOS). GAE can adjust the pause, ventilation and tones of synthesised audios automatically. This experimental conclusion may give some inspiration to researchers working on improving speech synthesis prosody.
Tasks Graph Embedding, Graph-to-Sequence, Speech Synthesis
Published 2020-03-04
URL https://arxiv.org/abs/2003.01924v1
PDF https://arxiv.org/pdf/2003.01924v1.pdf
PWC https://paperswithcode.com/paper/graphtts-graph-to-sequence-modelling-in

Robust Submodular Minimization with Applications to Cooperative Modeling

Title Robust Submodular Minimization with Applications to Cooperative Modeling
Authors Rishabh Iyer
Abstract Robust Optimization is becoming increasingly important in machine learning applications. This paper studies the problem of robust submodular minimization subject to combinatorial constraints. Constrained Submodular Minimization arises in several applications such as co-operative cuts in image segmentation, co-operative matchings in image correspondence, etc. Many of these models are defined over clusterings of data points (for example pixels in images), and it is important for these models to be robust to perturbations and uncertainty in the data. While several existing papers have studied robust submodular maximization, ours is the first work to study the minimization version under a broad range of combinatorial constraints including cardinality, knapsack, matroid as well as graph-based constraints such as cuts, paths, matchings, and trees. In each case, we provide scalable approximation algorithms and also study hardness bounds. Finally, we empirically demonstrate the utility of our algorithms on synthetic and real-world datasets.
Tasks Semantic Segmentation
Published 2020-01-25
URL https://arxiv.org/abs/2001.09360v1
PDF https://arxiv.org/pdf/2001.09360v1.pdf
PWC https://paperswithcode.com/paper/robust-submodular-minimization-with

SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor

Title SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
Authors Jiachen Xu, Jingyu Gong, Jie Zhou, Xin Tan, Yuan Xie, Lizhuang Ma
Abstract Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information and make full use of it. In this paper, we propose a SceneEncoder module to impose a scene-aware guidance to enhance the effect of global information. The module predicts a scene descriptor, which learns to represent the categories of objects existing in the scene and directly guides the point-level semantic segmentation through filtering out categories not belonging to this scene. Additionally, to alleviate segmentation noise in local region, we design a region similarity loss to propagate distinguishing features to their own neighboring points with the same label, leading to the enhancement of the distinguishing ability of point-wise features. We integrate our methods into several prevailing networks and conduct extensive experiments on benchmark datasets ScanNet and ShapeNet. Results show that our methods greatly improve the performance of baselines and achieve state-of-the-art performance.
Tasks Semantic Segmentation
Published 2020-01-24
URL https://arxiv.org/abs/2001.09087v1
PDF https://arxiv.org/pdf/2001.09087v1.pdf
PWC https://paperswithcode.com/paper/sceneencoder-scene-aware-semantic

Observer variation-aware medical image segmentation by combining deep learning and surrogate-assisted genetic algorithms

Title Observer variation-aware medical image segmentation by combining deep learning and surrogate-assisted genetic algorithms
Authors Arkadiy Dushatskiy, Adriënne M. Mendrik, Peter A. N. Bosman, Tanja Alderliesten
Abstract There has recently been great progress in automatic segmentation of medical images with deep learning algorithms. In most works observer variation is acknowledged to be a problem as it makes training data heterogeneous but so far no attempts have been made to explicitly capture this variation. Here, we propose an approach capable of mimicking different styles of segmentation, which potentially can improve quality and clinical acceptance of automatic segmentation methods. In this work, instead of training one neural network on all available data, we train several neural networks on subgroups of data belonging to different segmentation variations separately. Because a priori it may be unclear what styles of segmentation exist in the data and because different styles do not necessarily map one-on-one to different observers, the subgroups should be automatically determined. We achieve this by searching for the best data partition with a genetic algorithm. Therefore, each network can learn a specific style of segmentation from grouped training data. We provide proof of principle results for open-sourced prostate segmentation MRI data with simulated observer variations. Our approach provides an improvement of up to 23% (depending on simulated variations) in terms of Dice and surface Dice coefficients compared to one network trained on all data.
Tasks Medical Image Segmentation, Semantic Segmentation
Published 2020-01-23
URL https://arxiv.org/abs/2001.08552v1
PDF https://arxiv.org/pdf/2001.08552v1.pdf
PWC https://paperswithcode.com/paper/observer-variation-aware-medical-image

GPM: A Generic Probabilistic Model to Recover Annotator’s Behavior and Ground Truth Labeling

Title GPM: A Generic Probabilistic Model to Recover Annotator’s Behavior and Ground Truth Labeling
Authors Jing Li, Suiyi Ling, Junle Wang, Zhi Li, Patrick Le Callet
Abstract In the big data era, data labeling can be obtained through crowdsourcing. Nevertheless, the obtained labels are generally noisy, unreliable or even adversarial. In this paper, we propose a probabilistic graphical annotation model to infer the underlying ground truth and annotator’s behavior. To accommodate both discrete and continuous application scenarios (e.g., classifying scenes vs. rating videos on a Likert scale), the underlying ground truth is considered following a distribution rather than a single value. In this way, the reliable but potentially divergent opinions from “good” annotators can be recovered. The proposed model is able to identify whether an annotator has worked diligently towards the task during the labeling procedure, which could be used for further selection of qualified annotators. Our model has been tested on both simulated data and real-world data, where it always shows superior performance than the other state-of-the-art models in terms of accuracy and robustness.
Published 2020-03-01
URL https://arxiv.org/abs/2003.00475v1
PDF https://arxiv.org/pdf/2003.00475v1.pdf
PWC https://paperswithcode.com/paper/gpm-a-generic-probabilistic-model-to-recover
comments powered by Disqus