Related papers: MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

URL: http://arxiv.org/abs/2510.23013v1
Date: Mon, 27 Oct 2025 05:16:10 GMT
Title: MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning
Authors: Han Wu, Jie Yin,
Abstract summary: Few-shot knowledge graph relational learning seeks to perform reasoning over relations given only a limited number of training examples.<n>MoEMeta is a novel meta-learning framework that disentangles globally shared knowledge from task-specific contexts.
Score: 8.997817761465866
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Few-shot knowledge graph relational learning seeks to perform reasoning over relations given only a limited number of training examples. While existing approaches largely adopt a meta-learning framework for enabling fast adaptation to new relations, they suffer from two key pitfalls. First, they learn relation meta-knowledge in isolation, failing to capture common relational patterns shared across tasks. Second, they struggle to effectively incorporate local, task-specific contexts crucial for rapid adaptation. To address these limitations, we propose MoEMeta, a novel meta-learning framework that disentangles globally shared knowledge from task-specific contexts to enable both effective generalization and rapid adaptation. MoEMeta introduces two key innovations: (i) a mixture-of-experts (MoE) model that learns globally shared relational prototypes to enhance generalization, and (ii) a task-tailored adaptation mechanism that captures local contexts for fast task-specific adaptation. By balancing global generalization with local adaptability, MoEMeta significantly advances few-shot relational learning. Extensive experiments and analyses on three KG benchmarks demonstrate that MoEMeta consistently outperforms existing baselines, achieving state-of-the-art performance.

Related papers

Meta-Semantics Augmented Few-Shot Relational Learning [8.997817761465866]
Few-shot relational learning on knowledge graph (KGs) aims to perform reasoning over relations with only a few training examples.<n>We propose PromptMeta, a novel prompted meta-learning framework that seamlessly integrates meta-semantics with relational information.
arXiv Detail & Related papers (2025-05-08T22:59:42Z)
Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs [10.152109740331163]
We propose RelAdapter, a context-aware adapter for few-shot relation learning in knowledge graphs. First, RelAdapter is equipped with a lightweight adapter module that facilitates relation-specific, tunable adaptation of meta-knowledge. Second, RelAdapter is enriched with contextual information about the target relation, enabling enhanced adaptation to each distinct relation.
arXiv Detail & Related papers (2024-10-11T07:06:45Z)
Learning to Learn with Contrastive Meta-Objective [48.27877062976768]
We propose to exploit task identity as additional supervision in meta-training.<n>The proposed ConML is evaluating and optimizing the contrastive meta-objective.<n>We demonstrate that ConML integrates seamlessly with existing meta-learners, as well as in-context learning models.
arXiv Detail & Related papers (2024-10-08T12:22:10Z)
USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
arXiv Detail & Related papers (2023-01-17T12:42:58Z)
Meta-Learning with Self-Improving Momentum Target [72.98879709228981]
We propose Self-improving Momentum Target (SiMT) to improve the performance of a meta-learner. SiMT generates the target model by adapting from the temporal ensemble of the meta-learner. We show that SiMT brings a significant performance gain when combined with a wide range of meta-learning methods.
arXiv Detail & Related papers (2022-10-11T06:45:15Z)
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning [100.14809391594109]
Model-agnostic meta-learning (MAML) has emerged as one of the most successful meta-learning techniques in few-shot learning. Despite the generalization power of the meta-model, it remains elusive that how adversarial robustness can be maintained by MAML in few-shot learning. We propose a general but easily-optimized robustness-regularized meta-learning framework, which allows the use of unlabeled data augmentation, fast adversarial attack generation, and computationally-light fine-tuning.
arXiv Detail & Related papers (2021-02-20T22:03:04Z)
Improving Generalization in Meta-learning via Task Augmentation [69.83677015207527]
We propose two task augmentation methods, including MetaMix and Channel Shuffle. Both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets.
arXiv Detail & Related papers (2020-07-26T01:50:42Z)
Structured Prediction for Conditional Meta-Learning [44.30857707980074]
We propose a new perspective on conditional meta-learning via structured prediction. We derive task-adaptive structured meta-learning (TASML), a principled framework that yields task-specific objective functions. Empirically, we show that TASML improves the performance of existing meta-learning models, and outperforms the state-of-the-art on benchmark datasets.
arXiv Detail & Related papers (2020-02-20T15:24:15Z)
Automated Relational Meta-learning [95.02216511235191]
We propose an automated relational meta-learning framework that automatically extracts the cross-task relations and constructs the meta-knowledge graph. We conduct extensive experiments on 2D toy regression and few-shot image classification and the results demonstrate the superiority of ARML over state-of-the-art baselines.
arXiv Detail & Related papers (2020-01-03T07:02:25Z)

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