PyTorchKR Papers

최신 논문

총 2,097편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2302.03266공식 코드 · Papers with Code

Learning to Count Isomorphisms with Graph Neural Networks

Subgraph isomorphism counting is an important problem on graphs, as many graph-based tasks exploit recurring subgraph patterns. Classical methods usually boil down to a backtracking framework that needs to navigate a huge search space with prohibitive computational costs. Some recent studies resort to graph neural networks (GNNs) to learn a low-dimensional representation for both the query and input graphs, in order to predict the number of subgraph isomorphisms on the input graph. However, typical GNNs employ a node-centric message passing scheme that receives and aggregates messages on nodes, which is inadequate in complex structure matching for isomorphism counting. Moreover, on an input graph, the space of possible query graphs is enormous, and different parts of the input graph will be triggered to match different queries. Thus, expecting a fixed representation of the input graph to match diversely structured query graphs is unrealistic. In this paper, we propose a novel GNN called Count-GNN for subgraph isomorphism counting, to deal with the above challenges. At the edge level, given that an edge is an atomic unit of encoding graph structures, we propose an edge-centric message passing scheme, where messages on edges are propagated and aggregated based on the edge adjacency to preserve fine-grained structural information. At the graph level, we modulate the input graph representation conditioned on the query, so that the input graph can be adapted to each query individually to improve their matching. Finally, we conduct extensive experiments on a number of benchmark datasets to demonstrate the superior performance of Count-GNN.

arXiv:2302.01491

DiSProD: Differentiable Symbolic Propagation of Distributions for Planning

The paper introduces DiSProD, an online planner developed for environments with probabilistic transitions in continuous state and action spaces. DiSProD builds a symbolic graph that captures the distribution of future trajectories, conditioned on a given policy, using independence assumptions and approximate propagation of distributions. The symbolic graph provides a differentiable representation of the policy's value, enabling efficient gradient-based optimization for long-horizon search. The propagation of approximate distributions can be seen as an aggregation of many trajectories, making it well-suited for dealing with sparse rewards and stochastic environments. An extensive experimental evaluation compares DiSProD to state-of-the-art planners in discrete-time planning and real-time control of robotic systems. The proposed method improves over existing planners in handling stochastic environments, sensitivity to search depth, sparsity of rewards, and large action spaces. Additional real-world experiments demonstrate that DiSProD can control ground vehicles and surface vessels to successfully navigate around obstacles.

arXiv:2302.00767공식 코드 · Papers with Code

ImageNomer: description of a functional connectivity and omics analysis tool and case study identifying a race confound

Most packages for the analysis of fMRI-based functional connectivity (FC) and genomic data are used with a programming language interface, lacking an easy-to-navigate GUI frontend. This exacerbates two problems found in these types of data: demographic confounds and quality control in the face of high dimensionality of features. The reason is that it is too slow and cumbersome to use a programming interface to create all the necessary visualizations required to identify all correlations, confounding effects, or quality control problems in a dataset. To remedy this situation, we have developed ImageNomer, a data visualization and analysis tool that allows inspection of both subject-level and cohort-level demographic, genomic, and imaging features. The software is Python-based, runs in a self-contained Docker image, and contains a browser-based GUI frontend. We demonstrate the usefulness of ImageNomer by identifying an unexpected race confound when predicting achievement scores in the Philadelphia Neurodevelopmental Cohort (PNC) dataset. In the past, many studies have attempted to use FC to identify achievement-related features in fMRI. Using ImageNomer, we find a clear potential for confounding effects of race. Using correlation analysis in the ImageNomer software, we show that FCs correlated with Wide Range Achievement Test (WRAT) score are in fact more highly correlated with race. Investigating further, we find that whereas both FC and SNP (genomic) features can account for 10-15\% of WRAT score variation, this predictive ability disappears when controlling for race. In this work, we demonstrate the advantage of our ImageNomer GUI tool in data exploration and confound detection. Additionally, this work identifies race as a strong confound in FC data and casts doubt on the possibility of finding unbiased achievement-related features in fMRI and SNP data of healthy adolescents.

arXiv:2301.12457공식 코드 · Papers with Code

EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computation

Inspired by natural evolutionary processes, Evolutionary Computation (EC) has established itself as a cornerstone of Artificial Intelligence. Recently, with the surge in data-intensive applications and large-scale complex systems, the demand for scalable EC solutions has grown significantly. However, most existing EC infrastructures fall short of catering to the heightened demands of large-scale problem solving. While the advent of some pioneering GPU-accelerated EC libraries is a step forward, they also grapple with some limitations, particularly in terms of flexibility and architectural robustness. In response, we introduce EvoX: a computing framework tailored for automated, distributed, and heterogeneous execution of EC algorithms. At the core of EvoX lies a unique programming model to streamline the development of parallelizable EC algorithms, complemented by a computation model specifically optimized for distributed GPU acceleration. Building upon this foundation, we have crafted an extensive library comprising a wide spectrum of 50+ EC algorithms for both single- and multi-objective optimization. Furthermore, the library offers comprehensive support for a diverse set of benchmark problems, ranging from dozens of numerical test functions to hundreds of reinforcement learning tasks. Through extensive experiments across a range of problem scenarios and hardware configurations, EvoX demonstrates robust system and model performances. EvoX is open-source and accessible at: https://github.com/EMI-Group/EvoX.

arXiv:2301.12361

Graph Harmony: Denoising and Nuclear-Norm Wasserstein Adaptation for Enhanced Domain Transfer in Graph-Structured Data

Graph-structured data can be found in numerous domains, yet the scarcity of labeled instances hinders its effective utilization of deep learning in many scenarios. Traditional unsupervised domain adaptation (UDA) strategies for graphs primarily hinge on adversarial learning and pseudo-labeling. These approaches fail to effectively leverage graph discriminative features, leading to class mismatching and unreliable label quality. To navigate these obstacles, we develop the Denoising and Nuclear-Norm Wasserstein Adaptation Network (DNAN). DNAN employs the Nuclear-norm Wasserstein discrepancy (NWD), which can simultaneously achieve domain alignment and class distinguishment. DANA also integrates a denoising mechanism via a variational graph autoencoder that mitigates data noise. This denoising mechanism helps capture essential features of both source and target domains, improving the robustness of the domain adaptation process. Our comprehensive experiments demonstrate that DNAN outperforms state-of-the-art methods on standard UDA benchmarks for graph classification.

arXiv:2301.12351

Emerging Synergies in Causality and Deep Generative Models: A Survey

In the field of artificial intelligence (AI), the quest to understand and model data-generating processes (DGPs) is of paramount importance. Deep generative models (DGMs) have proven adept in capturing complex data distributions but often fall short in generalization and interpretability. On the other hand, causality offers a structured lens to comprehend the mechanisms driving data generation and highlights the causal-effect dynamics inherent in these processes. While causality excels in interpretability and the ability to extrapolate, it grapples with intricacies of high-dimensional spaces. Recognizing the synergistic potential, we delve into the confluence of causality and DGMs. We elucidate the integration of causal principles within DGMs, investigate causal identification using DGMs, and navigate an emerging research frontier of causality in large-scale generative models, particularly generative large language models (LLMs). We offer insights into methodologies, highlight open challenges, and suggest future directions, positioning our comprehensive review as an essential guide in this swiftly emerging and evolving area.

arXiv:2301.13166

ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation

The ability to accurately locate and navigate to a specific object is a crucial capability for embodied agents that operate in the real world and interact with objects to complete tasks. Such object navigation tasks usually require large-scale training in visual environments with labeled objects, which generalizes poorly to novel objects in unknown environments. In this work, we present a novel zero-shot object navigation method, Exploration with Soft Commonsense constraints (ESC), that transfers commonsense knowledge in pre-trained models to open-world object navigation without any navigation experience nor any other training on the visual environments. First, ESC leverages a pre-trained vision and language model for open-world prompt-based grounding and a pre-trained commonsense language model for room and object reasoning. Then ESC converts commonsense knowledge into navigation actions by modeling it as soft logic predicates for efficient exploration. Extensive experiments on MP3D, HM3D, and RoboTHOR benchmarks show that our ESC method improves significantly over baselines, and achieves new state-of-the-art results for zero-shot object navigation (e.g., 288% relative Success Rate improvement than CoW on MP3D).

arXiv:2301.08687

Counterexample Guided Abstraction Refinement with Non-Refined Abstractions for Multi-Agent Path Finding

Counterexample guided abstraction refinement (CEGAR) represents a powerful symbolic technique for various tasks such as model checking and reachability analysis. Recently, CEGAR combined with Boolean satisfiability (SAT) has been applied for multi-agent path finding (MAPF), a problem where the task is to navigate agents from their start positions to given individual goal positions so that the agents do not collide with each other. The recent CEGAR approach used the initial abstraction of the MAPF problem where collisions between agents were omitted and were eliminated in subsequent abstraction refinements. We propose in this work a novel CEGAR-style solver for MAPF based on SAT in which some abstractions are deliberately left non-refined. This adds the necessity to post-process the answers obtained from the underlying SAT solver as these answers slightly differ from the correct MAPF solutions. Non-refining however yields order-of-magnitude smaller SAT encodings than those of the previous approach and speeds up the overall solving process making the SAT-based solver for MAPF competitive again in relevant benchmarks.

arXiv:2301.08422공식 코드 · Papers with Code

A vision-based autonomous UAV inspection framework for unknown tunnel construction sites with dynamic obstacles

Tunnel construction using the drill-and-blast method requires the 3D measurement of the excavation front to evaluate underbreak locations. Considering the inspection and measurement task's safety, cost, and efficiency, deploying lightweight autonomous robots, such as unmanned aerial vehicles (UAV), becomes more necessary and popular. Most of the previous works use a prior map for inspection viewpoint determination and do not consider dynamic obstacles. To maximally increase the level of autonomy, this paper proposes a vision-based UAV inspection framework for dynamic tunnel environments without using a prior map. Our approach utilizes a hierarchical planning scheme, decomposing the inspection problem into different levels. The high-level decision maker first determines the task for the robot and generates the target point. Then, the mid-level path planner finds the waypoint path and optimizes the collision-free static trajectory. Finally, the static trajectory will be fed into the low-level local planner to avoid dynamic obstacles and navigate to the target point. Besides, our framework contains a novel dynamic map module that can simultaneously track dynamic obstacles and represent static obstacles based on an RGB-D camera. After inspection, the Structure-from-Motion (SfM) pipeline is applied to generate the 3D shape of the target. To our best knowledge, this is the first time autonomous inspection has been realized in unknown and dynamic tunnel environments. Our flight experiments in a real tunnel prove that our method can autonomously inspect the tunnel excavation front surface. Our software is available on GitHub as an open-source ROS package.

arXiv:2301.08278공식 코드 · Papers with Code

Investigating the Impact of Direct Punishment on the Emergence of Cooperation in Multi-Agent Reinforcement Learning Systems

Solving the problem of cooperation is fundamentally important for the creation and maintenance of functional societies. Problems of cooperation are omnipresent within human society, with examples ranging from navigating busy road junctions to negotiating treaties. As the use of AI becomes more pervasive throughout society, the need for socially intelligent agents capable of navigating these complex cooperative dilemmas is becoming increasingly evident. Direct punishment is a ubiquitous social mechanism that has been shown to foster the emergence of cooperation in both humans and non-humans. In the natural world, direct punishment is often strongly coupled with partner selection and reputation and used in conjunction with third-party punishment. The interactions between these mechanisms could potentially enhance the emergence of cooperation within populations. However, no previous work has evaluated the learning dynamics and outcomes emerging from Multi-Agent Reinforcement Learning (MARL) populations that combine these mechanisms. This paper addresses this gap. It presents a comprehensive analysis and evaluation of the behaviors and learning dynamics associated with direct punishment, third-party punishment, partner selection, and reputation. Finally, we discuss the implications of using these mechanisms on the design of cooperative AI systems.

arXiv:2301.07979공식 코드 · Papers with Code

Endogenous Labour Flow Networks

In the last decade, the study of labour dynamics has led to the introduction of labour flow networks (LFNs) as a way to conceptualise job-to-job transitions, and to the development of mathematical models to explore the dynamics of these networked flows. To date, LFN models have relied upon an assumption of static network structure. However, as recent events (increasing automation in the workplace, the COVID-19 pandemic, a surge in the demand for programming skills, etc.) have shown, we are experiencing drastic shifts to the job landscape that are altering the ways individuals navigate the labour market. Here we develop a novel model that emerges LFNs from agent-level behaviour, removing the necessity of assuming that future job-to-job flows will be along the same paths where they have been historically observed. This model, informed by microdata for the United Kingdom, generates empirical LFNs with a high level of accuracy. We use the model to explore how shocks impacting the underlying distributions of jobs and wages alter the topology of the LFN. This framework represents a crucial step towards the development of models that can answer questions about the future of work in an ever-changing world.

arXiv:2301.07302

PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav

We study ObjectGoal Navigation -- where a virtual robot situated in a new environment is asked to navigate to an object. Prior work has shown that imitation learning (IL) using behavior cloning (BC) on a dataset of human demonstrations achieves promising results. However, this has limitations -- 1) BC policies generalize poorly to new states, since the training mimics actions not their consequences, and 2) collecting demonstrations is expensive. On the other hand, reinforcement learning (RL) is trivially scalable, but requires careful reward engineering to achieve desirable behavior. We present PIRLNav, a two-stage learning scheme for BC pretraining on human demonstrations followed by RL-finetuning. This leads to a policy that achieves a success rate of $65.0\%$ on ObjectNav ($+5.0\%$ absolute over previous state-of-the-art). Using this BC$\rightarrow$RL training recipe, we present a rigorous empirical analysis of design choices. First, we investigate whether human demonstrations can be replaced with `free' (automatically generated) sources of demonstrations, e.g. shortest paths (SP) or task-agnostic frontier exploration (FE) trajectories. We find that BC$\rightarrow$RL on human demonstrations outperforms BC$\rightarrow$RL on SP and FE trajectories, even when controlled for same BC-pretraining success on train, and even on a subset of val episodes where BC-pretraining success favors the SP or FE policies. Next, we study how RL-finetuning performance scales with the size of the BC pretraining dataset. We find that as we increase the size of BC-pretraining dataset and get to high BC accuracies, improvements from RL-finetuning are smaller, and that $90\%$ of the performance of our best BC$\rightarrow$RL policy can be achieved with less than half the number of BC demonstrations. Finally, we analyze failure modes of our ObjectNav policies, and present guidelines for further improving them.

arXiv:2301.03363

Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning

This paper proposes an adaptable path tracking control system based on Reinforcement Learning (RL) for autonomous cars. A four-parameter controller shapes the behavior of the vehicle to navigate on lane changes and roundabouts. The tuning of the tracker uses an educated Q-Learning algorithm to minimize the lateral and steering trajectory errors. The CARLA simulation environment was used both for training and testing. The results show the vehicle is able to adapt its behavior to the different types of reference trajectories, navigating safely with low tracking errors. The use of a ROS bridge between the CARLA and the tracker results (i) in a realistic system, and (ii) simplifies the replacement of the CARLA by a real vehicle. An argument on the dependability of the overall architecture based on stability results of non-smooth systems is presented at the end of the paper.

arXiv:2301.00964

e-Inu: Simulating A Quadruped Robot With Emotional Sentience

Quadruped robots are currently used in industrial robotics as mechanical aid to automate several routine tasks. However, presently, the usage of such a robot in a domestic setting is still very much a part of the research. This paper discusses the understanding and virtual simulation of such a robot capable of detecting and understanding human emotions, generating its gait, and responding via sounds and expression on a screen. To this end, we use a combination of reinforcement learning and software engineering concepts to simulate a quadruped robot that can understand emotions, navigate through various terrains and detect sound sources, and respond to emotions using audio-visual feedback. This paper aims to establish the framework of simulating a quadruped robot that is emotionally intelligent and can primarily respond to audio-visual stimuli using motor or audio response. The emotion detection from the speech was not as performant as ERANNs or Zeta Policy learning, still managing an accuracy of 63.5%. The video emotion detection system produced results that are almost at par with the state of the art, with an accuracy of 99.66%. Due to its "on-policy" learning process, the PPO algorithm was extremely rapid to learn, allowing the simulated dog to demonstrate a remarkably seamless gait across the different cadences and variations. This enabled the quadruped robot to respond to generated stimuli, allowing us to conclude that it functions as predicted and satisfies the aim of this work.

arXiv:2212.14800

A deep real options policy for sequential service region design and timing

As various city agencies and mobility operators navigate toward innovative mobility solutions, there is a need for strategic flexibility in well-timed investment decisions in the design and timing of mobility service regions, i.e. cast as "real options" (RO). This problem becomes increasingly challenging with multiple interacting RO in such investments. We propose a scalable machine learning based RO framework for multi-period sequential service region design & timing problem for mobility-on-demand services, framed as a Markov decision process with non-stationary stochastic variables. A value function approximation policy from literature uses multi-option least squares Monte Carlo simulation to get a policy value for a set of interdependent investment decisions as deferral options (CR policy). The goal is to determine the optimal selection and timing of a set of zones to include in a service region. However, prior work required explicit enumeration of all possible sequences of investments. To address the combinatorial complexity of such enumeration, we propose a new variant "deep" RO policy using an efficient recurrent neural network (RNN) based ML method (CR-RNN policy) to sample sequences to forego the need for enumeration, making network design & timing policy tractable for large scale implementation. Experiments on multiple service region scenarios in New York City (NYC) shows the proposed policy substantially reduces the overall computational cost (time reduction for RO evaluation of > 90% of total investment sequences is achieved), with zero to near-zero gap compared to the benchmark. A case study of sequential service region design for expansion of MoD services in Brooklyn, NYC show that using the CR-RNN policy to determine optimal RO investment strategy yields a similar performance (0.5% within CR policy value) with significantly reduced computation time (about 5.4 times faster).

arXiv:2212.13824

Multi-Realism Image Compression with a Conditional Generator

By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models. However, previous methods do not explicitly control how much detail is synthesized, which results in a common criticism of these methods: users might be worried that a misleading reconstruction far from the input image is generated. In this work, we alleviate these concerns by training a decoder that can bridge the two regimes and navigate the distortion-realism trade-off. From a single compressed representation, the receiver can decide to either reconstruct a low mean squared error reconstruction that is close to the input, a realistic reconstruction with high perceptual quality, or anything in between. With our method, we set a new state-of-the-art in distortion-realism, pushing the frontier of achievable distortion-realism pairs, i.e., our method achieves better distortions at high realism and better realism at low distortion than ever before.

arXiv:2212.13415공식 코드 · Papers with Code

Spacecraft Pose Estimation Based on Unsupervised Domain Adaptation and on a 3D-Guided Loss Combination

Spacecraft pose estimation is a key task to enable space missions in which two spacecrafts must navigate around each other. Current state-of-the-art algorithms for pose estimation employ data-driven techniques. However, there is an absence of real training data for spacecraft imaged in space conditions due to the costs and difficulties associated with the space environment. This has motivated the introduction of 3D data simulators, solving the issue of data availability but introducing a large gap between the training (source) and test (target) domains. We explore a method that incorporates 3D structure into the spacecraft pose estimation pipeline to provide robustness to intensity domain shift and we present an algorithm for unsupervised domain adaptation with robust pseudo-labelling. Our solution has ranked second in the two categories of the 2021 Pose Estimation Challenge organised by the European Space Agency and the Stanford University, achieving the lowest average error over the two categories.

arXiv:2212.12185

Implementation of a Blind navigation method in outdoors/indoors areas

According to WHO statistics, the number of visually impaired people is increasing annually. One of the most critical necessities for visually impaired people is the ability to navigate safely. This paper proposes a navigation system based on the visual slam and Yolo algorithm using monocular cameras. The proposed system consists of three steps: obstacle distance estimation, path deviation detection, and next-step prediction. Using the ORB-SLAM algorithm, the proposed method creates a map from a predefined route and guides the users to stay on the route while notifying them if they deviate from it. Additionally, the system utilizes the YOLO algorithm to detect obstacles along the route and alert the user. The experimental results, obtained by using a laptop camera, show that the proposed system can run in 30 frame per second while guiding the user within predefined routes of 11 meters in indoors and outdoors. The accuracy of the positioning system is 8cm, and the system notifies the users if they deviate from the predefined route by more than 60 cm.

arXiv:2212.11482

Learning to swim efficiently in a nonuniform flow field

Microswimmers can acquire information on the surrounding fluid by sensing mechanical queues. They can then navigate in response to these signals. We analyse this navigation by combining deep reinforcement learning with direct numerical simulations to resolve the hydrodynamics. We study how local and non-local information can be used to train a swimmer to achieve particular swimming tasks in a non-uniform flow field, in particular a zig-zag shear flow. The swimming tasks are (1) learning how to swim in the vorticity direction, (2) the shear-gradient direction, and (3) the shear flow direction. We find that access to lab frame information on the swimmer's instantaneous orientation is all that is required in order to reach the optimal policy for (1,2). However, information on both the translational and rotational velocities seem to be required to achieve (3). Inspired by biological microorganisms we also consider the case where the swimmers sense local information, i.e. surface hydrodynamic forces, together with a signal direction. This might correspond to gravity or, for micro-organisms with light sensors, a light source. In this case, we show that the swimmer can reach a comparable level of performance as a swimmer with access to lab frame variables. We also analyse the role of different swimming modes, i.e. pusher, puller, and neutral swimmers.

arXiv:2212.11182

Universal versus system-specific features of punctuation usage patterns in~major Western~languages

The celebrated proverb that "speech is silver, silence is golden" has a long multinational history and multiple specific meanings. In written texts punctuation can in fact be considered one of its manifestations. Indeed, the virtue of effectively speaking and writing involves - often decisively - the capacity to apply the properly placed breaks. In the present study, based on a large corpus of world-famous and representative literary texts in seven major Western languages, it is shown that the distribution of intervals between consecutive punctuation marks in almost all texts can universally be characterised by only two parameters of the discrete Weibull distribution which can be given an intuitive interpretation in terms of the so-called hazard function. The values of these two parameters tend to be language-specific, however, and even appear to navigate translations. The properties of the computed hazard functions indicate that among the studied languages, English turns out to be the least constrained by the necessity to place a consecutive punctuation mark to partition a sequence of words. This may suggest that when compared to other studied languages, English is more flexible, in the sense of allowing longer uninterrupted sequences of words. Spanish reveals similar tendency to only a bit lesser extent.