Separating the what and how of compositional computation to enable reuse and continual learning

• URL: http://arxiv.org/abs/2510.20709v1
• Date: Thu, 23 Oct 2025 16:24:40 GMT
• Title: Separating the what and how of compositional computation to enable reuse and continual learning
• Authors: Haozhe Shan, Sun Minni, Lea Duncker,
• Abstract summary: We study continual learning and the compositional reuse of learned computations in recurrent neural network (RNN) models.<n>We first show that a large family of tasks can be systematically described by a probabilistic generative model.<n>We develop an unsupervised online learning approach that can learn this model on a single-trial basis.
• Score: 1.8206461789819075
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability to continually learn, retain and deploy skills to accomplish goals is a key feature of intelligent and efficient behavior. However, the neural mechanisms facilitating the continual learning and flexible (re-)composition of skills remain elusive. Here, we study continual learning and the compositional reuse of learned computations in recurrent neural network (RNN) models using a novel two-system approach: one system that infers what computation to perform, and one that implements how to perform it. We focus on a set of compositional cognitive tasks commonly studied in neuroscience. To construct the what system, we first show that a large family of tasks can be systematically described by a probabilistic generative model, where compositionality stems from a shared underlying vocabulary of discrete task epochs. The shared epoch structure makes these tasks inherently compositional. We first show that this compositionality can be systematically described by a probabilistic generative model. Furthermore, We develop an unsupervised online learning approach that can learn this model on a single-trial basis, building its vocabulary incrementally as it is exposed to new tasks, and inferring the latent epoch structure as a time-varying computational context within a trial. We implement the how system as an RNN whose low-rank components are composed according to the context inferred by the what system. Contextual inference facilitates the creation, learning, and reuse of low-rank RNN components as new tasks are introduced sequentially, enabling continual learning without catastrophic forgetting. Using an example task set, we demonstrate the efficacy and competitive performance of this two-system learning framework, its potential for forward and backward transfer, as well as fast compositional generalization to unseen tasks.

Related papers

• Compositional meta-learning through probabilistic task inference [35.701036869822836]
  We propose a compositional meta-learning model that represents tasks as structured combinations of reusable computations.<n>This approach transforms learning a new task into a probabilistic inference problem.<n>We demonstrate its ability to quickly infer new solutions from just single examples.
  arXiv  Detail & Related papers  (2025-10-02T09:58:48Z)
• A Unified Framework for Neural Computation and Learning Over Time [56.44910327178975]
  Hamiltonian Learning is a novel unified framework for learning with neural networks "over time" It is based on differential equations that: (i) can be integrated without the need of external software solvers; (ii) generalize the well-established notion of gradient-based learning in feed-forward and recurrent networks; (iii) open to novel perspectives.
  arXiv  Detail & Related papers  (2024-09-18T14:57:13Z)
• Hierarchically Structured Task-Agnostic Continual Learning [0.0]
  We take a task-agnostic view of continual learning and develop a hierarchical information-theoretic optimality principle. We propose a neural network layer, called the Mixture-of-Variational-Experts layer, that alleviates forgetting by creating a set of information processing paths. Our approach can operate in a task-agnostic way, i.e., it does not require task-specific knowledge, as is the case with many existing continual learning algorithms.
  arXiv  Detail & Related papers  (2022-11-14T19:53:15Z)
• Neural-Symbolic Recursive Machine for Systematic Generalization [113.22455566135757]
  We introduce the Neural-Symbolic Recursive Machine (NSR), whose core is a Grounded Symbol System (GSS) NSR integrates neural perception, syntactic parsing, and semantic reasoning. We evaluate NSR's efficacy across four challenging benchmarks designed to probe systematic generalization capabilities.
  arXiv  Detail & Related papers  (2022-10-04T13:27:38Z)
• Learning and Compositionality: a Unification Attempt via Connectionist Probabilistic Programming [11.06543250284755]
  We consider learning and compositionality as the key mechanisms towards simulating human-like intelligence. We propose Connectionist Probabilistic Program ( CPP), a framework that connects connectionist structures (for learning) and probabilistic program semantics (for compositionality)
  arXiv  Detail & Related papers  (2022-08-26T17:20:58Z)
• Lifelong Machine Learning of Functionally Compositional Structures [7.99536002595393]
  This dissertation presents a general-purpose framework for lifelong learning of functionally compositional structures. The framework separates the learning into two stages: learning how to combine existing components to assimilate a novel problem, and learning how to adapt the existing components to accommodate the new problem. Supervised learning evaluations found that 1) compositional models improve lifelong learning of diverse tasks, 2) the multi-stage process permits lifelong learning of compositional knowledge, and 3) the components learned by the framework represent self-contained and reusable functions.
  arXiv  Detail & Related papers  (2022-07-25T15:24:25Z)
• Sparsely ensembled convolutional neural network classifiers via reinforcement learning [0.0]
  We consider convolutional neural network (CNN) ensemble learning with the objective function inspired by least action principle. We teach an agent to perceive images through the set of pre-trained classifiers and want the resulting dynamically configured system to unfold the computational graph. Our experimental results prove, that if the agent exploits the dynamic (and context-dependent) structure of computations, it outperforms conventional ensemble learning.
  arXiv  Detail & Related papers  (2021-02-07T21:26:57Z)
• Network Classifiers Based on Social Learning [71.86764107527812]
  We propose a new way of combining independently trained classifiers over space and time. The proposed architecture is able to improve prediction performance over time with unlabeled data. We show that this strategy results in consistent learning with high probability, and it yields a robust structure against poorly trained classifiers.
  arXiv  Detail & Related papers  (2020-10-23T11:18:20Z)
• 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)
• Adversarial Continual Learning [99.56738010842301]
  We propose a hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features. Our model combines architecture growth to prevent forgetting of task-specific skills and an experience replay approach to preserve shared skills.
  arXiv  Detail & Related papers  (2020-03-21T02:08:17Z)
• A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning [48.87397222244402]
  We propose an expansion-based approach for task-free continual learning. Our model successfully performs task-free continual learning for both discriminative and generative tasks.
  arXiv  Detail & Related papers  (2020-01-03T02:07:31Z)

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.