Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs

• URL: http://arxiv.org/abs/2410.09123v2
• Date: Thu, 17 Oct 2024 07:00:29 GMT
• Title: Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs
• Authors: Ran Liu, Zhongzhou Liu, Xiaoli Li, Yuan Fang,
• Abstract summary: 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.
• Score: 10.152109740331163
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge graphs (KGs) are instrumental in various real-world applications, yet they often suffer from incompleteness due to missing relations. To predict instances for novel relations with limited training examples, few-shot relation learning approaches have emerged, utilizing techniques such as meta-learning. However, the assumption is that novel relations in meta-testing and base relations in meta-training are independently and identically distributed, which may not hold in practice. To address the limitation, we propose RelAdapter, a context-aware adapter for few-shot relation learning in KGs designed to enhance the adaptation process in meta-learning. First, RelAdapter is equipped with a lightweight adapter module that facilitates relation-specific, tunable adaptation of meta-knowledge in a parameter-efficient manner. Second, RelAdapter is enriched with contextual information about the target relation, enabling enhanced adaptation to each distinct relation. Extensive experiments on three benchmark KGs validate the superiority of RelAdapter over state-of-the-art methods.

Related papers

• MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning [8.997817761465866]
  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.
  arXiv  Detail & Related papers  (2025-10-27T05:16:10Z)
• FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs [15.157416257109809]
  Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations.<n>We propose FusionAdapter for the learning of few-shot relationships in MMKGs.<n>By effectively adapting and fusing information from diverse modalities, FusionAdapter improves generalization to novel relations with minimal supervision.
  arXiv  Detail & Related papers  (2025-10-01T13:36:56Z)
• ART: Adaptive Relation Tuning for Generalized Relation Prediction [33.15138052099355]
  Visual relation detection (VRD) is the task of identifying the relationships between objects in a scene.<n>While prompt tuning has been used to adapt vision-language models (VLMs) for VRD, it uses handcrafted prompts and struggles with novel or complex relations.<n>We argue that instruction tuning offers a more effective solution by fine-tuning VLMs on diverse instructional data.
  arXiv  Detail & Related papers  (2025-07-31T13:34:06Z)
• In-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory [54.92893355284945]
  Deep learning-based wireless receivers offer the potential to dynamically adapt to varying channel environments.<n>Current adaptation strategies, including joint training, hypernetwork-based methods, and meta-learning, either demonstrate limited flexibility or necessitate explicit optimization through gradient descent.<n>This paper presents gradient-free adaptation techniques rooted in the emerging paradigm of in-context learning (ICL)
  arXiv  Detail & Related papers  (2025-06-18T06:43:55Z)
• Prompted Meta-Learning for Few-shot Knowledge Graph Completion [11.880512693272367]
  Few-shot knowledge graph completion (KGC) has obtained significant attention due to its practical applications in real-world scenarios.<n>We propose a novel prompted meta-learning framework that seamlessly integrates meta-semantics with relational information for few-shot KGC.<n>PrompMeta has two key innovations: (1) a meta-semantic prompt pool that captures and consolidates high-level meta-semantics, enabling effective knowledge transfer and adaptation to rare and newly emerging relations.
  arXiv  Detail & Related papers  (2025-05-08T22:59:42Z)
• Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass [109.34230156454574]
  Large language models (LMs) are typically adapted to improve performance on new contexts. fine-tuning incurs significant training cost and prompting increases inference overhead. We introduce $GenerativeAdapter$, an effective and efficient adaptation method that directly maps new contexts to low-rank LM adapters.
  arXiv  Detail & Related papers  (2024-11-08T00:42:47Z)
• Rethinking Meta-Learning from a Learning Lens [35.98940987691948]
  We consider how to bridge the gap between theoretical understanding and practical implementation of meta-learning.<n>We propose TRLearner, a plug-and-play method that leverages task relation to calibrate meta-learning.
  arXiv  Detail & Related papers  (2024-09-13T02:00:16Z)
• CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning [101.81127587760831]
  Current fine-tuning methods build adapters widely of the context of downstream task to learn, or the context of important knowledge to maintain. We propose CorDA, a Context-oriented Decomposition Adaptation method that builds learnable task-aware adapters. Our method enables two options, the knowledge-preserved adaptation and the instruction-previewed adaptation.
  arXiv  Detail & Related papers  (2024-06-07T19:10:35Z)
• Semantic-Enhanced Relational Metric Learning for Recommender Systems [27.330164862413184]
  Recently, metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. We propose a joint Semantic-Enhanced Metric Learning framework to tackle the problem in recommender systems. Specifically the semantic signal is first extracted from the target reviews containing abundant features and personalized user preferences. A novel regression model is then designed via leveraging the extracted semantic signal to improve the discriminative ability of original relation-based training process.
  arXiv  Detail & Related papers  (2024-06-07T11:54:50Z)
• Modeling Balanced Explicit and Implicit Relations with Contrastive Learning for Knowledge Concept Recommendation in MOOCs [1.0377683220196874]
  Existing methods rely on the explicit relations between users and knowledge concepts for recommendation. There are numerous implicit relations generated within the users' learning activities on the MOOC platforms. We propose a novel framework based on contrastive learning, which can represent and balance the explicit and implicit relations.
  arXiv  Detail & Related papers  (2024-02-13T07:12:44Z)
• Type-based Neural Link Prediction Adapter for Complex Query Answering [2.1098688291287475]
  We propose TypE-based Neural Link Prediction Adapter (TENLPA), a novel model that constructs type-based entity-relation graphs. In order to effectively combine type information with complex logical queries, an adaptive learning mechanism is introduced. Experiments on 3 standard datasets show that TENLPA model achieves state-of-the-art performance on complex query answering.
  arXiv  Detail & Related papers  (2024-01-29T10:54:28Z)
• Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion [25.905974480733562]
  We propose a hierarchical relational learning method (HiRe) for few-shot KG completion. By jointly capturing three levels of relational information, HiRe can effectively learn and refine the meta representation of few-shot relations. Experiments on two benchmark datasets validate the superiority of HiRe against other state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-09-02T17:57:03Z)
• Hybrid Relation Guided Set Matching for Few-shot Action Recognition [51.3308583226322]
  We propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components. The purpose of the hybrid relation module is to learn task-specific embeddings by fully exploiting associated relations within and cross videos in an episode. We evaluate HyRSM on six challenging benchmarks, and the experimental results show its superiority over the state-of-the-art methods by a convincing margin.
  arXiv  Detail & Related papers  (2022-04-28T11:43:41Z)
• Subgraph-aware Few-Shot Inductive Link Prediction via Meta-Learning [16.288230150590046]
  We propose Meta-iKG, a novel subgraph-based meta-learner for few-shot inductive relation reasoning. We find the model can quickly adapt to few-shot relationships using only a handful of known facts with inductive settings.
  arXiv  Detail & Related papers  (2021-07-26T11:56:18Z)
• Meta-learning the Learning Trends Shared Across Tasks [123.10294801296926]
  Gradient-based meta-learning algorithms excel at quick adaptation to new tasks with limited data. Existing meta-learning approaches only depend on the current task information during the adaptation. We propose a 'Path-aware' model-agnostic meta-learning approach.
  arXiv  Detail & Related papers  (2020-10-19T08:06:47Z)
• Revisiting Meta-Learning as Supervised Learning [69.2067288158133]
  We aim to provide a principled, unifying framework by revisiting and strengthening the connection between meta-learning and traditional supervised learning. By treating pairs of task-specific data sets and target models as (feature, label) samples, we can reduce many meta-learning algorithms to instances of supervised learning. This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning.
  arXiv  Detail & Related papers  (2020-02-03T06:13:01Z)
• Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs [96.73259297063619]
  We consider a novel formulation, zero-shot learning, to free this cumbersome curation. For newly-added relations, we attempt to learn their semantic features from their text descriptions. We leverage Generative Adrial Networks (GANs) to establish the connection between text and knowledge graph domain.
  arXiv  Detail & Related papers  (2020-01-08T01:19:08Z)

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.