Related papers: Adapting, Fast and Slow: Transportable Circuits for Few-Shot Learning

Adapting, Fast and Slow: Transportable Circuits for Few-Shot Learning

URL: http://arxiv.org/abs/2512.22777v1
Date: Sun, 28 Dec 2025 04:38:43 GMT
Title: Adapting, Fast and Slow: Transportable Circuits for Few-Shot Learning
Authors: Kasra Jalaldoust, Elias Bareinboim,
Abstract summary: Generalization across the domains is not possible without asserting a structure that constrains the unseen target domain w.r.t.<n>We design an algorithm for zero-shot compositional generalization which relies on access to qualitative domain knowledge.<n>Our theoretical results characterize classes of few-shot learnable tasks in terms of graphical circuit transportability criteria.
Score: 54.930879235929204
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Generalization across the domains is not possible without asserting a structure that constrains the unseen target domain w.r.t. the source domain. Building on causal transportability theory, we design an algorithm for zero-shot compositional generalization which relies on access to qualitative domain knowledge in form of a causal graph for intra-domain structure and discrepancies oracle for inter-domain mechanism sharing. \textit{Circuit-TR} learns a collection of modules (i.e., local predictors) from the source data, and transport/compose them to obtain a circuit for prediction in the target domain if the causal structure licenses. Furthermore, circuit transportability enables us to design a supervised domain adaptation scheme that operates without access to an explicit causal structure, and instead uses limited target data. Our theoretical results characterize classes of few-shot learnable tasks in terms of graphical circuit transportability criteria, and connects few-shot generalizability with the established notion of circuit size complexity; controlled simulations corroborate our theoretical results.

Related papers

A Unified Analysis of Generalization and Sample Complexity for Semi-Supervised Domain Adaptation [1.9567015559455132]
Domain adaptation seeks to leverage the abundant label information in a source domain to improve classification performance in a target domain with limited labels.<n>Most existing theoretical analyses focus on simplified settings where the source and target domains share the same input space.<n>We present a comprehensive theoretical study of domain adaptation algorithms based on domain alignment.
arXiv Detail & Related papers (2025-07-30T12:53:08Z)
A Pre-training Framework for Relational Data with Information-theoretic Principles [57.93973948947743]
We introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs supervisory signals via set-based aggregation over relational graphs.<n>TVE consistently outperforms traditional pre-training baselines.<n>Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases.
arXiv Detail & Related papers (2025-07-14T00:17:21Z)
Partial Transportability for Domain Generalization [56.37032680901525]
Building on the theory of partial identification and transportability, this paper introduces new results for bounding the value of a functional of the target distribution.<n>Our contribution is to provide the first general estimation technique for transportability problems.<n>We propose a gradient-based optimization scheme for making scalable inferences in practice.
arXiv Detail & Related papers (2025-03-30T22:06:37Z)
Logifold: A Geometrical Foundation of Ensemble Machine Learning [0.0]
We present a local-to-global and measure-theoretical approach to understanding datasets. The core idea is to formulate a logifold structure and to interpret network models with restricted domains as local charts of datasets.
arXiv Detail & Related papers (2024-07-23T04:47:58Z)
DIGIC: Domain Generalizable Imitation Learning by Causal Discovery [69.13526582209165]
Causality has been combined with machine learning to produce robust representations for domain generalization. We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy. We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
arXiv Detail & Related papers (2024-02-29T07:09:01Z)
Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain [7.012240324005977]
Shortcut learning occurs when a deep neural network overly relies on spurious correlations in the training dataset to solve downstream tasks. We propose a novel approach to mitigate shortcut learning in uncontrolled target domains.
arXiv Detail & Related papers (2022-07-20T16:05:32Z)
Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection [81.07378219410182]
We propose a new and general framework for DomainD, named Foreground-aware Graph-based Reasoning (FGRR) FGRR incorporates graph structures into the detection pipeline to explicitly model the intra- and inter-domain foreground object relations. Empirical results demonstrate that the proposed FGRR exceeds the state-of-the-art on four DomainD benchmarks.
arXiv Detail & Related papers (2022-06-06T05:12:48Z)
Unsupervised Domain Adaptation for Image Classification via Structure-Conditioned Adversarial Learning [70.79486026698419]
Unsupervised domain adaptation (UDA) typically carries out knowledge transfer from a label-rich source domain to an unlabeled target domain by adversarial learning. We propose an end-to-end structure-conditioned adversarial learning scheme (SCAL) that is able to preserve the intra-class compactness during domain distribution alignment.
arXiv Detail & Related papers (2021-03-04T03:12:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.