Toward Compositional Generalization in Object-Oriented World Modeling

• URL: http://arxiv.org/abs/2204.13661v1
• Date: Thu, 28 Apr 2022 17:22:45 GMT
• Title: Toward Compositional Generalization in Object-Oriented World Modeling
• Authors: Linfeng Zhao, Lingzhi Kong, Robin Walters, Lawson L.S. Wong
• Abstract summary: We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modeling. We introduce a conceptual environment, Object Library, and two instances, and deploy a principled pipeline to measure the generalization ability. Motivated by the formulation, we analyze several methods with exact or no compositional generalization ability using our framework, and design a differentiable approach, Homomorphic Object-oriented World Model (HOWM)
• Score: 6.463111870767873
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modeling. We (1) formalize the compositional generalization problem with an algebraic approach and (2) study how a world model can achieve that. We introduce a conceptual environment, Object Library, and two instances, and deploy a principled pipeline to measure the generalization ability. Motivated by the formulation, we analyze several methods with exact} or no compositional generalization ability using our framework, and design a differentiable approach, Homomorphic Object-oriented World Model (HOWM), that achieves approximate but more efficient compositional generalization.

Related papers

• What makes Models Compositional? A Theoretical View: With Supplement [60.284698521569936]
  We propose a general neuro-symbolic definition of compositional functions and their compositional complexity. We show how various existing general and special purpose sequence processing models fit this definition and use it to analyze their compositional complexity.
  arXiv  Detail & Related papers  (2024-05-02T20:10:27Z)
• Position Paper: Generalized grammar rules and structure-based generalization beyond classical equivariance for lexical tasks and transduction [7.523978255716284]
  We propose a general framework for building models that can generalize compositionally using the concept of Generalized Grammar Rules (GGRs) Our framework is general enough to contain many existing works as special cases. We present ideas on how GGRs might be implemented, and in the process draw connections to reinforcement learning and other areas of research.
  arXiv  Detail & Related papers  (2024-02-02T18:44:37Z)
• Provable Compositional Generalization for Object-Centric Learning [57.42720932595342]
  Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. We show that autoencoders that satisfy structural assumptions on the decoder and enforce encoder-decoder consistency will learn object-centric representations that provably generalize compositionally.
  arXiv  Detail & Related papers  (2023-10-09T01:18:07Z)
• Compositional Generalization from First Principles [27.243195680442533]
  We investigate compositionality as a property of the data-generating process rather than the data itself. This reformulation enables us to derive mild conditions on only the support of the training distribution and the model architecture. Our results set the stage for a principled theoretical study of compositional generalization.
  arXiv  Detail & Related papers  (2023-07-10T19:30:32Z)
• Compositional Generalisation with Structured Reordering and Fertility Layers [121.37328648951993]
  Seq2seq models have been shown to struggle with compositional generalisation. We present a flexible end-to-end differentiable neural model that composes two structural operations.
  arXiv  Detail & Related papers  (2022-10-06T19:51:31Z)
• Abstract Interpretation for Generalized Heuristic Search in Model-Based Planning [50.96320003643406]
  Domain-general model-based planners often derive their generality by constructing searchs through the relaxation of symbolic world models. We illustrate how abstract interpretation can serve as a unifying framework for these abstractions, extending the reach of search to richer world models. Theses can also be integrated with learning, allowing agents to jumpstart planning in novel world models via abstraction-derived information.
  arXiv  Detail & Related papers  (2022-08-05T00:22:11Z)
• Improving Compositional Generalization in Classification Tasks via Structure Annotations [33.90268697120572]
  Humans have a great ability to generalize compositionally, but state-of-the-art neural models struggle to do so. First, we study ways to convert a natural language sequence-to-sequence dataset to a classification dataset that also requires compositional generalization. Second, we show that providing structural hints (specifically, providing parse trees and entity links as attention masks for a Transformer model) helps compositional generalization.
  arXiv  Detail & Related papers  (2021-06-19T06:07:27Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• Compositional Generalization by Learning Analytical Expressions [87.15737632096378]
  A memory-augmented neural model is connected with analytical expressions to achieve compositional generalization. Experiments on the well-known benchmark SCAN demonstrate that our model seizes a great ability of compositional generalization.
  arXiv  Detail & Related papers  (2020-06-18T15:50:57Z)
• Deep Sets for Generalization in RL [15.092941080981706]
  This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. In a 2D procedurally-generated world where agents targeting goals in natural language navigate and interact with objects, we show that these architectures demonstrate strong generalization capacities to out-of-distribution goals.
  arXiv  Detail & Related papers  (2020-03-20T18:22:40Z)

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.