Statistical relational learning (SRL) and graph neural networks (GNNs) are two powerful approaches for learning and inference over graphs. Typically, they are evaluated in terms of simple metrics such as accuracy over individual node labels. Complex
SocNavBench: A Grounded Simulation Testing Framework for Evaluating Social Navigation
The human-robot interaction community has developed many methods for robots to navigate safely and socially alongside humans. However, experimental procedures to evaluate these works are usually constructed on a per-method basis. Such disparate evaluations make it difficult to compare the performance of such methods across the literature. To bridge this gap, we introduce SocNavBench , a simulation framework for evaluating social navigation algorithms. SocNavBench comprises a simulator with photo-realistic capabilities and curated social navigation scenarios grounded in real-world pedestrian data. We also provide an implementation of a suite of metrics to quantify the performance of navigation algorithms on these scenarios. Altogether, SocNavBench provides a test framework for evaluating disparate social navigation methods in a consistent and interpretable manner. To illustrate its use, we demonstrate testing three existing social navigation methods and a baseline method on SocNavBench , showing how the suite of metrics helps infer their performance trade-offs. Our code is open-source, allowing the addition of new scenarios and metrics by the community to help evolve SocNavBench to reflect advancements in our understanding of social navigation.
more »
« less
- Award ID(s):
- 1734361
- NSF-PAR ID:
- 10341305
- Date Published:
- Journal Name:
- ACM Transactions on Human-Robot Interaction
- Volume:
- 11
- Issue:
- 3
- ISSN:
- 2573-9522
- Page Range / eLocation ID:
- 1 to 24
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract aggregate graph queries (AGQ) involving multiple nodes, edges, and labels are common in the graph mining community and are used to estimate important network properties such as social cohesion and influence. While graph mining algorithms support AGQs, they typically do not take into account uncertainty, or when they do, make simplifying assumptions and do not build full probabilistic models. In this paper, we examine the performance of SRL and GNNs on AGQs over graphs with partially observed node labels. We show that, not surprisingly, inferring the unobserved node labels as a first step and then evaluating the queries on the fully observed graph can lead to sub-optimal estimates, and that a better approach is to compute these queries as an expectation under the joint distribution. We propose a sampling framework to tractably compute the expected values of AGQs. Motivated by the analysis of subgroup cohesion in social networks, we propose a suite of AGQs that estimate the community structure in graphs. In our empirical evaluation, we show that by estimating these queries as an expectation, SRL-based approaches yield up to a 50-fold reduction in average error when compared to existing GNN-based approaches. -
Scientific breakthroughs in biomolecular methods and improvements in hardware technology have shifted from a single long-running simulation to a large set of shorter simulations running simultaneously, called an ensemble. In an ensemble, each independent simulation is usually coupled with several analyses that apply identical or distinct algorithms on data produced by the corresponding simulation. Today, In situ methods are used to analyze large volumes of data generated by scientific simulations at runtime. This work studies the execution of ensemble-based simulations paired with In situ analyses using in-memory staging methods. Because simulations and analyses forming an ensemble typically run concurrently, deploying an ensemble requires efficient co-location-aware strategies, making sure the data flow between simulations and analyses that form an In situ workflow is efficient. Using an ensemble of molecular dynamics In situ workflows with multiple simulations and analyses, we first show that collecting traditional metrics such as makespan, instructions per cycle, memory usage, or cache miss ratio is not sufficient to characterize the complex behaviors of ensembles. Thus, we propose a method to evaluate the performance of ensembles of workflows that captures resource usage (efficiency), resource allocation, and component placement. Experimental results demonstrate that our proposed method can effectively capture the performance of different component placements in an ensemble. By evaluating different co-location scenarios, our performance indicator demonstrates improvements of up to four orders of magnitude when co-locating simulation and coupled analyses within a single computational host.more » « less
-
more » « less
Abstract Although infrequent, large (Mw7.5+) earthquakes can be extremely damaging and occur on subduction and intraplate faults worldwide. Earthquake early warning (EEW) systems aim to provide advanced warning before strong shaking and tsunami onsets. These systems estimate earthquake magnitude using the early metrics of waveforms, relying on empirical scaling relationships of abundant past events. However, both the rarity and complexity of great events make it challenging to characterize them, and EEW algorithms often underpredict magnitude and the resulting hazards. Here, we propose a model, M‐LARGE, that leverages deep learning to characterize crustal deformation patterns of large earthquakes for a specific region in real‐time. We demonstrate the algorithm in the Chilean Subduction Zone by training it with more than six million different simulated rupture scenarios recorded on the Chilean GNSS network. M‐LARGE performs reliable magnitude estimation on the testing data set with an accuracy of 99%. Furthermore, the model successfully predicts the magnitude of five real Chilean earthquakes that occurred in the last 11 years. These events were damaging, large enough to be recorded by the modern high rate global navigation satellite system instrument, and provide valuable ground truth. M‐LARGE tracks the evolution of the source process and can make faster and more accurate magnitude estimation, significantly outperforming other similar EEW algorithms. This is the first demonstration of our approach. Future work toward generalization is outstanding and will include the addition of more training and testing data, interfacing with existing EEW methods, and applying the method to different tectonic settings to explore performance in these regions.
-
Machine-learning models are known to be vulnerable to evasion attacks, which perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where the threat cannot be assessed accurately by existing attacks. Specifically, we find that conventional metrics measuring targeted and untargeted robustness do not appropriately reflect a model’s ability to withstand attacks from one set of source classes to another set of target classes. To address the shortcomings of existing methods, we formally define a new metric, termed group-based robustness, that complements existing metrics and is better suited for evaluating model performance in certain attack scenarios. We show empirically that group-based robustness allows us to distinguish between machine-learning models’ vulnerability against specific threat models in situations where traditional robustness metrics do not apply. Moreover, to measure group-based robustness efficiently and accurately, we 1) propose two loss functions and 2) identify three new attack strategies. We show empirically that, with comparable success rates, finding evasive samples using our new loss functions saves computation by a factor as large as the number of targeted classes, and that finding evasive samples, using our new attack strategies, saves time by up to 99% compared to brute-force search methods. Finally, we propose a defense method that increases group-based robustness by up to 3.52 times.more » « less
-
Scientific breakthroughs in biomolecular methods and improvements in hardware technology have shifted from a long-running simulation to a large set of shorter simulations running simultaneously, called an ensemble. In an ensemble, simulations are usually coupled with analyses of data produced by the simulations. In situ methods can be used to analyze large volumes of data generated by scientific simulations at runtime (i.e., simulations and analyses are performed concurrently). In this work, we study the execution of ensemble-based simulations paired with in situ analyses using in-memory staging methods. Using an ensemble of molecular dynamics in situ workflows with multiple simulations and analyses, we first show that collecting traditional metrics such as makespan, instructions per cycle, memory usage, or cache miss ratio is not sufficient to characterize complex behaviors of ensembles. We propose a method to evaluate the performance of ensembles of workflows that captures multiple resource usage aspects: resource efficiency, resource allocation, and resource provisioning. Experimental results demonstrate that the proposed method can effectively distinguish the performance of different component placements in an ensemble with up to 32 ensemble members. By evaluating different co-location scenarios, our proposed performance indicators demonstrate benefits of co-locating simulation and coupled analyses within a compute node.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1145/3476413
