Observing a group to infer individual characteristics

• URL: http://arxiv.org/abs/2110.05864v1
• Date: Tue, 12 Oct 2021 09:59:54 GMT
• Title: Observing a group to infer individual characteristics
• Authors: Arshed Nabeel and Danny Raj M
• Abstract summary: We propose a new observer algorithm that infers, based only on observed movement information, how the local neighborhood aids or hinders agent movement. Unlike a traditional supervised learning approach, this algorithm is based on physical insights and scaling arguments, and does not rely on training-data. Data-agnostic approaches like this have relevance to a large class of real-world problems where clean, labeled data is difficult to obtain.
• Score: 1.0152838128195465
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the study of collective motion, it is common practice to collect movement information at the level of the group to infer the characteristics of the individual agents and their interactions. However, it is not clear whether one can always correctly infer individual characteristics from movement data of the collective. We investigate this question in the context of a composite crowd with two groups of agents, each with its own desired direction of motion. A simple observer attempts to classify an agent into its group based on its movement information. However, collective effects such as collisions, entrainment of agents, formation of lanes and clusters, etc. render the classification problem non-trivial, and lead to misclassifications. Based on our understanding of these effects, we propose a new observer algorithm that infers, based only on observed movement information, how the local neighborhood aids or hinders agent movement. Unlike a traditional supervised learning approach, this algorithm is based on physical insights and scaling arguments, and does not rely on training-data. This new observer improves classification performance and is able to differentiate agents belonging to different groups even when their motion is identical. Data-agnostic approaches like this have relevance to a large class of real-world problems where clean, labeled data is difficult to obtain, and is a step towards hybrid approaches that integrate both data and domain knowledge.

Related papers

• Consistency Based Weakly Self-Supervised Learning for Human Activity Recognition with Wearables [1.565361244756411]
  We describe a weakly self-supervised approach for recognizing human activities from sensor-based data. We show that our approach can help the clustering algorithm achieve comparable performance in identifying and categorizing the underlying human activities.
  arXiv  Detail & Related papers  (2024-07-29T06:29:21Z)
• Explaining Clustering of Ecological Momentary Assessment Data Through Temporal and Feature Attention [4.951599300340955]
  Ecological Momentary Assessment (EMA) studies offer rich individual data on psychopathology-relevant variables in real-time. This paper proposes an attention-based interpretable framework to identify the important time-points and variables that play primary roles in distinguishing between clusters.
  arXiv  Detail & Related papers  (2024-05-08T07:09:43Z)
• Leveraging sparse and shared feature activations for disentangled representation learning [112.22699167017471]
  We propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. We validate our approach on six real world distribution shift benchmarks, and different data modalities.
  arXiv  Detail & Related papers  (2023-04-17T01:33:24Z)
• Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitions [51.71245032890532]
  We propose methods enabling an agent acting upon the world to learn internal representations of sensory information consistent with actions that modify it. In contrast to existing work, our approach does not require prior knowledge of the group and does not restrict the set of actions the agent can perform.
  arXiv  Detail & Related papers  (2022-07-25T11:22:48Z)
• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution [77.85461690214551]
  Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution. Recent self-supervised learning methods have shown to be effective when dealing with fully-unlabeled data in cases where the underlying classes have significant semantic differences. We propose a strategy to tackle Person Re-Identification and Text Authorship Attribution by enabling learning from unlabeled data even when samples from different classes are not prominently diverse.
  arXiv  Detail & Related papers  (2022-02-07T13:08:11Z)
• Fair Group-Shared Representations with Normalizing Flows [68.29997072804537]
  We develop a fair representation learning algorithm which is able to map individuals belonging to different groups in a single group. We show experimentally that our methodology is competitive with other fair representation learning algorithms.
  arXiv  Detail & Related papers  (2022-01-17T10:49:49Z)
• Towards Group Robustness in the presence of Partial Group Labels [61.33713547766866]
  spurious correlations between input samples and the target labels wrongly direct the neural network predictions. We propose an algorithm that optimize for the worst-off group assignments from a constraint set. We show improvements in the minority group's performance while preserving overall aggregate accuracy across groups.
  arXiv  Detail & Related papers  (2022-01-10T22:04:48Z)
• GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer [16.988878921451484]
  GroupFormer captures spatial-temporal contextual information jointly to augment the individual and group representations. The proposed framework outperforms state-of-the-art methods on the Volleyball dataset and Collective Activity dataset.
  arXiv  Detail & Related papers  (2021-08-28T11:24:36Z)
• You Never Cluster Alone [150.94921340034688]
  We extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation. We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps.
  arXiv  Detail & Related papers  (2021-06-03T14:59:59Z)
• DETECT: Deep Trajectory Clustering for Mobility-Behavior Analysis [10.335486459171992]
  We propose an unsupervised neural approach for mobility behavior clustering, called Deep Embedded TrajEctor ClusTering network (DETECT) DETECT operates in three parts: first it transforms the trajectories by summarizing their critical parts and augmenting them with context derived from their geographical locality. In the second part, it learns a powerful representation of trajectories in the latent space of behaviors, thus enabling a clustering function (such as $k$means) to be applied.
  arXiv  Detail & Related papers  (2020-03-03T06:09:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.