Memorizing Long-tail Data Can Help Generalization Through Composition

• URL: http://arxiv.org/abs/2510.16322v1
• Date: Sat, 18 Oct 2025 03:11:53 GMT
• Title: Memorizing Long-tail Data Can Help Generalization Through Composition
• Authors: Mo Zhou, Haoyang Ma, Rong Ge,
• Abstract summary: We consider the synergy between memorization and simple composition.<n>We show that for a linear setting, memorization together with composition can help the model make correct predictions.
• Score: 25.046184437410346
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning has led researchers to rethink the relationship between memorization and generalization. In many settings, memorization does not hurt generalization due to implicit regularization and may help by memorizing long-tailed examples. In this paper, we consider the synergy between memorization and simple composition -- the ability to make correct prediction on a combination of long-tailed features. Theoretically, we show that for a linear setting, memorization together with composition can help the model make correct predictions on rare test examples that require a combination of long-tailed features, even if such combinations were never observed in the training data. Experiments on neural network architecture on simple data show that the theoretical insight extends beyond the linear setting, and we further observe that the composition capability of the model depends on its architecture.

Related papers

• Does Data Scaling Lead to Visual Compositional Generalization? [21.242714408660508]
  We find that compositional generalization is driven by data diversity, not mere data scale.<n>We prove this structure is key to efficiency, enabling perfect generalization from few observed combinations.
  arXiv  Detail & Related papers  (2025-07-09T17:59:03Z)
• Explainable Neural Networks with Guarantees: A Sparse Estimation Approach [11.142723510517778]
  This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability.<n>Our model, termed SparXnet, is designed as a linear combination of a sparse set of jointly learned features.<n>Our research paves the way for further research on sparse and explainable neural networks with guarantee.
  arXiv  Detail & Related papers  (2025-01-02T12:10:17Z)
• When does compositional structure yield compositional generalization? A kernel theory [0.0]
  We present a theory of compositional generalization in kernel models with fixed, compositionally structured representations.<n>We identify novel failure modes in compositional generalization that arise from biases in the training data.<n>This work examines how statistical structure in the training data can affect compositional generalization.
  arXiv  Detail & Related papers  (2024-05-26T00:50:11Z)
• 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)
• Decoupling Knowledge from Memorization: Retrieval-augmented Prompt Learning [113.58691755215663]
  We develop RetroPrompt to help a model strike a balance between generalization and memorization. In contrast with vanilla prompt learning, RetroPrompt constructs an open-book knowledge-store from training instances. Extensive experiments demonstrate that RetroPrompt can obtain better performance in both few-shot and zero-shot settings.
  arXiv  Detail & Related papers  (2022-05-29T16:07:30Z)
• Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning [109.7767515627765]
  We propose a new semiparametric paradigm of retrieval-enhanced prompt tuning for relation extraction. Our model infers relation through knowledge stored in the weights during training. Our method can achieve state-of-the-art in both standard supervised and few-shot settings.
  arXiv  Detail & Related papers  (2022-05-04T23:38:37Z)
• Towards Differential Relational Privacy and its use in Question Answering [109.4452196071872]
  Memorization of relation between entities in a dataset can lead to privacy issues when using a trained question answering model. We quantify this phenomenon and provide a possible definition of Differential Privacy (DPRP) We illustrate concepts in experiments with largescale models for Question Answering.
  arXiv  Detail & Related papers  (2022-03-30T22:59:24Z)
• Deep Learning Through the Lens of Example Difficulty [21.522182447513632]
  We introduce a measure of the computational difficulty of making a prediction for a given input: the (effective) prediction depth. Our investigation reveals surprising yet simple relationships between the prediction depth of a given input and the model's uncertainty, confidence, accuracy and speed of learning for that data point.
  arXiv  Detail & Related papers  (2021-06-17T16:48:12Z)
• Learning compositional structures for semantic graph parsing [81.41592892863979]
  We show how AM dependency parsing can be trained directly on a neural latent-variable model. Our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training.
  arXiv  Detail & Related papers  (2021-06-08T14:20:07Z)
• Compositional Processing Emerges in Neural Networks Solving Math Problems [100.80518350845668]
  Recent progress in artificial neural networks has shown that when large models are trained on enough linguistic data, grammatical structure emerges in their representations. We extend this work to the domain of mathematical reasoning, where it is possible to formulate precise hypotheses about how meanings should be composed. Our work shows that neural networks are not only able to infer something about the structured relationships implicit in their training data, but can also deploy this knowledge to guide the composition of individual meanings into composite wholes.
  arXiv  Detail & Related papers  (2021-05-19T07:24:42Z)
• Parsimonious Inference [0.0]
  Parsimonious inference is an information-theoretic formulation of inference over arbitrary architectures. Our approaches combine efficient encodings with prudent sampling strategies to construct predictive ensembles without cross-validation.
  arXiv  Detail & Related papers  (2021-03-03T04:13:14Z)
• 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.