Provable Compositional Generalization for Object-Centric Learning

• URL: http://arxiv.org/abs/2310.05327v2
• Date: Tue, 12 Nov 2024 15:34:57 GMT
• Title: Provable Compositional Generalization for Object-Centric Learning
• Authors: Thaddäus Wiedemer, Jack Brady, Alexander Panfilov, Attila Juhos, Matthias Bethge, Wieland Brendel,
• Abstract summary: 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.
• Score: 55.658215686626484
• License:
• Abstract: Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learning object-centric representations, which are widely conjectured to enable compositional generalization. Yet, it remains unclear when this conjecture will be true, as a principled theoretical or empirical understanding of compositional generalization is lacking. In this work, we investigate when compositional generalization is guaranteed for object-centric representations through the lens of identifiability theory. 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. We validate our theoretical result and highlight the practical relevance of our assumptions through experiments on synthetic image data.

Related papers

• When does compositional structure yield compositional generalization? A kernel theory [0.0]
  We present a theory of compositional generalization in kernel models with fixed representations. We identify novel failure modes in compositional generalization that arise from biases in the training data. This work provides a theoretical perspective on how statistical structure in the training data can affect compositional generalization.
  arXiv  Detail & Related papers  (2024-05-26T00:50:11Z)
• 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)
• Vector-based Representation is the Key: A Study on Disentanglement and Compositional Generalization [77.57425909520167]
  We show that it is possible to achieve both good concept recognition and novel concept composition. We propose a method to reform the scalar-based disentanglement works to be vector-based to increase both capabilities.
  arXiv  Detail & Related papers  (2023-05-29T13:05:15Z)
• Provably Learning Object-Centric Representations [25.152680199034215]
  We analyze when object-centric representations can provably be learned without supervision. We prove that the ground-truth object representations can be identified by an invertible and compositional inference model. We provide evidence that our theory holds predictive power for existing object-centric models.
  arXiv  Detail & Related papers  (2023-05-23T16:44:49Z)
• Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis [10.29814984060018]
  We consider a kernel-based contrastive learning framework termed Kernel Contrastive Learning (KCL) We introduce a formulation of the similarity structure of learned representations by utilizing a statistical dependency viewpoint. We show a new upper bound of the classification error of a downstream task, which explains that our theory is consistent with the empirical success of contrastive learning.
  arXiv  Detail & Related papers  (2023-04-01T21:53:29Z)
• Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language [48.37815764394315]
  We study three unsupervised representation learning algorithms on two datasets that allow directly testing compositional generalization. We find that directly using the bottleneck representation with simple models and few labels may lead to worse generalization than using representations from layers before or after the learned representation itself. Surprisingly, we find that increasing pressure to produce a disentangled representation produces representations with worse generalization, while representations from EL models show strong compositional generalization.
  arXiv  Detail & Related papers  (2022-10-02T10:35:53Z)
• Disentangled Sequence to Sequence Learning for Compositional Generalization [62.954842223732435]
  We propose an extension to sequence-to-sequence models which allows us to learn disentangled representations by adaptively re-encoding the source input. Experimental results on semantic parsing and machine translation empirically show that our proposal yields more disentangled representations and better generalization.
  arXiv  Detail & Related papers  (2021-10-09T22:27:19Z)
• Concepts, Properties and an Approach for Compositional Generalization [2.0559497209595823]
  This report connects a series of our work for compositional generalization, and summarizes an approach. The approach uses architecture design and regularization to regulate information of representations. We hope this work would be helpful to clarify fundamentals of compositional generalization and lead to advance artificial intelligence.
  arXiv  Detail & Related papers  (2021-02-08T14:22:30Z)
• Formalising Concepts as Grounded Abstractions [68.24080871981869]
  This report shows how representation learning can be used to induce concepts from raw data. The main technical goal of this report is to show how techniques from representation learning can be married with a lattice-theoretic formulation of conceptual spaces.
  arXiv  Detail & Related papers  (2021-01-13T15:22:01Z)
• 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)

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.