Revisit Systematic Generalization via Meaningful Learning

• URL: http://arxiv.org/abs/2003.06658v5
• Date: Tue, 18 Oct 2022 07:36:12 GMT
• Title: Revisit Systematic Generalization via Meaningful Learning
• Authors: Ning Shi, Boxin Wang, Wei Wang, Xiangyu Liu, Zhouhan Lin
• Abstract summary: Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity. We reassess the compositional skills of sequence-to-sequence models conditioned on the semantic links between new and old concepts.
• Score: 15.90288956294373
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans can systematically generalize to novel compositions of existing concepts. Recent studies argue that neural networks appear inherently ineffective in such cognitive capacity, leading to a pessimistic view and a lack of attention to optimistic results. We revisit this controversial topic from the perspective of meaningful learning, an exceptional capability of humans to learn novel concepts by connecting them with known ones. We reassess the compositional skills of sequence-to-sequence models conditioned on the semantic links between new and old concepts. Our observations suggest that models can successfully one-shot generalize to novel concepts and compositions through semantic linking, either inductively or deductively. We demonstrate that prior knowledge plays a key role as well. In addition to synthetic tests, we further conduct proof-of-concept experiments in machine translation and semantic parsing, showing the benefits of meaningful learning in applications. We hope our positive findings will encourage excavating modern neural networks' potential in systematic generalization through more advanced learning schemes.

Related papers

• Restyling Unsupervised Concept Based Interpretable Networks with Generative Models [14.604305230535026]
  We propose a novel method that relies on mapping the concept features to the latent space of a pretrained generative model. We quantitatively ascertain the efficacy of our method in terms of accuracy of the interpretable prediction network, fidelity of reconstruction, as well as faithfulness and consistency of learnt concepts.
  arXiv  Detail & Related papers  (2024-07-01T14:39:41Z)
• From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks [0.0]
  We review recent empirical work from machine learning for a broad audience in philosophy, cognitive science, and neuroscience. In particular, our review emphasizes two approaches to endowing neural networks with compositional generalization capabilities. We conclude by discussing the implications that these findings may have for the study of compositionality in human cognition.
  arXiv  Detail & Related papers  (2024-05-24T02:36:07Z)
• Distilling Symbolic Priors for Concept Learning into Neural Networks [9.915299875869046]
  We show that inductive biases can be instantiated in artificial neural networks by distilling a prior distribution from a symbolic Bayesian model via meta-learning. We use this approach to create a neural network with an inductive bias towards concepts expressed as short logical formulas.
  arXiv  Detail & Related papers  (2024-02-10T20:06:26Z)
• From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks [15.837316393474403]
  Concepts can act as a natural link between learning and reasoning. Knowledge can not only be extracted from neural networks but concept knowledge can also be inserted into neural network architectures.
  arXiv  Detail & Related papers  (2023-10-18T11:08:02Z)
• Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization [49.00409552570441]
  We study the role of conceptualization in commonsense reasoning, and formulate a framework to replicate human conceptual induction. We apply the framework to ATOMIC, a large-scale human-annotated CKG, aided by the taxonomy Probase.
  arXiv  Detail & Related papers  (2022-06-03T12:24:49Z)
• What can linearized neural networks actually say about generalization? [67.83999394554621]
  In certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization. We show that the linear approximations can indeed rank the learning complexity of certain tasks for neural networks. Our work provides concrete examples of novel deep learning phenomena which can inspire future theoretical research.
  arXiv  Detail & Related papers  (2021-06-12T13:05:11Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness [63.627760598441796]
  We provide an in-depth review of the field of adversarial robustness in deep learning. We highlight the intuitive connection between adversarial examples and the geometry of deep neural networks. We provide an overview of the main emerging applications of adversarial robustness beyond security.
  arXiv  Detail & Related papers  (2020-10-19T16:03:46Z)
• 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)
• Generating new concepts with hybrid neuro-symbolic models [22.336243882030026]
  Human conceptual knowledge supports the ability to generate novel yet highly structured concepts. One tradition has emphasized structured knowledge, viewing concepts as embedded in intuitive theories or organized in complex symbolic knowledge structures. A second tradition has emphasized statistical knowledge, viewing conceptual knowledge as an emerging from the rich correlational structure captured by training neural networks and other statistical models.
  arXiv  Detail & Related papers  (2020-03-19T18:45:56Z)

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.