Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models

• URL: http://arxiv.org/abs/2402.09236v1
• Date: Wed, 14 Feb 2024 15:23:59 GMT
• Title: Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models
• Authors: Goutham Rajendran, Simon Buchholz, Bryon Aragam, Bernhard Sch\"olkopf, Pradeep Ravikumar
• Abstract summary: We study how to learn human-interpretable concepts from data. Weaving together ideas from both fields, we show that concepts can be provably recovered from diverse data.
• Score: 51.43538150982291
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causal representation learning. The other approach is to build highly-performant foundation models and then invest efforts into understanding how they work. In this work, we relate these two approaches and study how to learn human-interpretable concepts from data. Weaving together ideas from both fields, we formally define a notion of concepts and show that they can be provably recovered from diverse data. Experiments on synthetic data and large language models show the utility of our unified approach.

Related papers

• Big Cooperative Learning [7.958840888809145]
  We show that the training of foundation models can be interpreted as a form of big cooperative learning. We propose the BigLearn-GAN, which is a novel adversarially-trained foundation model with versatile data sampling capabilities.
  arXiv  Detail & Related papers  (2024-07-31T03:59:14Z)
• CoLiDR: Concept Learning using Aggregated Disentangled Representations [29.932706137805713]
  Interpretability of Deep Neural Networks using concept-based models offers a promising way to explain model behavior through human-understandable concepts. A parallel line of research focuses on disentangling the data distribution into its underlying generative factors, in turn explaining the data generation process. While both directions have received extensive attention, little work has been done on explaining concepts in terms of generative factors to unify mathematically disentangled representations and human-understandable concepts.
  arXiv  Detail & Related papers  (2024-07-27T16:55:14Z)
• Heterogeneous Contrastive Learning for Foundation Models and Beyond [73.74745053250619]
  In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive self-supervised learning to model large-scale heterogeneous data. This survey critically evaluates the current landscape of heterogeneous contrastive learning for foundation models.
  arXiv  Detail & Related papers  (2024-03-30T02:55:49Z)
• Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition [83.13280812128411]
  Recent studies have uncovered intriguing phenomena in deep learning, such as grokking, double descent, and emergent abilities in large language models. We present a comprehensive framework that provides a unified view of these three phenomena, focusing on the competition between memorization and generalization circuits.
  arXiv  Detail & Related papers  (2024-02-23T08:14:36Z)
• Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
  Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
  arXiv  Detail & Related papers  (2023-07-25T17:59:18Z)
• 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)
• Inspecting the concept knowledge graph encoded by modern language models [5.2117321443066364]
  We study the underlying knowledge encoded by nine of the most influential language models of the last years. Our results reveal that all the models encode this knowledge, but suffer from several inaccuracies. We conduct a systematic evaluation to discover specific factors that explain why some concepts are challenging.
  arXiv  Detail & Related papers  (2021-05-27T22:19:19Z)
• 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)
• 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)

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.