Learning Hierarchical Relational Representations through Relational
Convolutions
- URL: http://arxiv.org/abs/2310.03240v2
- Date: Tue, 20 Feb 2024 20:21:18 GMT
- Title: Learning Hierarchical Relational Representations through Relational
Convolutions
- Authors: Awni Altabaa, John Lafferty
- Abstract summary: We propose an architectural framework we call "relational convolutional networks"
We formalize a relational convolution operation in which graphlet filters are matched against patches of the input.
We also propose mechanisms for explicitly learning groupings of objects which are relevant to the downstream task.
- Score: 2.99146123420045
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A maturing area of research in deep learning is the study of architectures
and inductive biases for learning representations of relational features. In
this paper, we focus on the problem of learning representations of hierarchical
relations, proposing an architectural framework we call "relational
convolutional networks". Given a collection of objects, pairwise relations are
modeled via inner products of feature maps. We formalize a relational
convolution operation in which graphlet filters are matched against patches of
the input (i.e, groupings of objects), capturing the relational pattern in each
group of objects. We also propose mechanisms for explicitly learning groupings
of objects which are relevant to the downstream task. Composing these
operations yields representations of higher-order, hierarchical relations. We
present the motivation and details of the architecture, together with a set of
experiments to demonstrate how relational convolutional networks can provide an
effective framework for modeling relational tasks that have hierarchical
structure.
Related papers
- Structural Concept Learning via Graph Attention for Multi-Level
Rearrangement Planning [2.7195102129095003]
We propose a deep learning approach to perform multi-level object rearrangement planning for scenes with structural dependency hierarchies.
It is trained on a self-generated simulation data set with intuitive structures and works for unseen scenes with an arbitrary number of objects.
We compare our method with a range of classical and model-based baselines to show that our method leverages its scene understanding to achieve better performance, flexibility, and efficiency.
arXiv Detail & Related papers (2023-09-05T19:35:44Z) - Geometric Relational Embeddings: A Survey [39.57716353191535]
We survey methods that underly geometric relational embeddings and categorize them based on the embedding geometries that are used to represent the data.
We identify the desired properties (i.e., inductive biases) of each kind of embedding and discuss some potential future work.
arXiv Detail & Related papers (2023-04-24T09:33:30Z) - ViRel: Unsupervised Visual Relations Discovery with Graph-level Analogy [65.5580334698777]
ViRel is a method for unsupervised discovery and learning of Visual Relations with graph-level analogy.
We show that our method achieves above 95% accuracy in relation classification.
We further generalizes to unseen tasks with more complicated relational structures.
arXiv Detail & Related papers (2022-07-04T16:56:45Z) - On Neural Architecture Inductive Biases for Relational Tasks [76.18938462270503]
We introduce a simple architecture based on similarity-distribution scores which we name Compositional Network generalization (CoRelNet)
We find that simple architectural choices can outperform existing models in out-of-distribution generalizations.
arXiv Detail & Related papers (2022-06-09T16:24:01Z) - Unified Graph Structured Models for Video Understanding [93.72081456202672]
We propose a message passing graph neural network that explicitly models relational-temporal relations.
We show how our method is able to more effectively model relationships between relevant entities in the scene.
arXiv Detail & Related papers (2021-03-29T14:37:35Z) - Adaptive Interaction Modeling via Graph Operations Search [109.45125932109454]
We automate the process of structures design to learn adaptive structures for interaction modeling.
We experimentally demonstrate that our architecture search framework learns to construct adaptive interaction modeling structures.
Our method achieves competitive performance with state-of-the-arts.
arXiv Detail & Related papers (2020-05-05T13:01:09Z) - Dynamic Language Binding in Relational Visual Reasoning [67.85579756590478]
We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains.
Our method outperforms other methods in sophisticated question-answering tasks wherein multiple object relations are involved.
arXiv Detail & Related papers (2020-04-30T06:26:20Z) - Bidirectional Graph Reasoning Network for Panoptic Segmentation [126.06251745669107]
We introduce a Bidirectional Graph Reasoning Network (BGRNet) to mine the intra-modular and intermodular relations within and between foreground things and background stuff classes.
BGRNet first constructs image-specific graphs in both instance and semantic segmentation branches that enable flexible reasoning at the proposal level and class level.
arXiv Detail & Related papers (2020-04-14T02:32:10Z)
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.