A Framework of Meta Functional Learning for Regularising Knowledge Transfer

• URL: http://arxiv.org/abs/2203.14840v1
• Date: Mon, 28 Mar 2022 15:24:09 GMT
• Title: A Framework of Meta Functional Learning for Regularising Knowledge Transfer
• Authors: Pan Li, Yanwei Fu and Shaogang Gong
• Abstract summary: This work proposes a novel framework of Meta Functional Learning (MFL) by meta-learning a generalisable functional model from data-rich tasks. The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned.
• Score: 89.74127682599898
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning classifiers' capability is largely dependent on the scale of available training data and limited by the model overfitting in data-scarce learning tasks. To address this problem, this work proposes a novel framework of Meta Functional Learning (MFL) by meta-learning a generalisable functional model from data-rich tasks whilst simultaneously regularising knowledge transfer to data-scarce tasks. The MFL computes meta-knowledge on functional regularisation generalisable to different learning tasks by which functional training on limited labelled data promotes more discriminative functions to be learned. Based on this framework, we formulate three variants of MFL: MFL with Prototypes (MFL-P) which learns a functional by auxiliary prototypes, Composite MFL (ComMFL) that transfers knowledge from both functional space and representational space, and MFL with Iterative Updates (MFL-IU) which improves knowledge transfer regularisation from MFL by progressively learning the functional regularisation in knowledge transfer. Moreover, we generalise these variants for knowledge transfer regularisation from binary classifiers to multi-class classifiers. Extensive experiments on two few-shot learning scenarios, Few-Shot Learning (FSL) and Cross-Domain Few-Shot Learning (CD-FSL), show that meta functional learning for knowledge transfer regularisation can improve FSL classifiers.

Related papers

• TaSL: Task Skill Localization and Consolidation for Language Model Continual Learning [41.28933724210434]
  Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. Existing approaches commonly utilize multiple parameter-efficient fine-tuning (PEFT) blocks to acquire task-specific knowledge, yet these methods are inefficient and fail to leverage potential knowledge transfer across tasks. We introduce a novel CL framework for language models, named Task Skill Localization and Consolidation (TaSL), which boosts knowledge transfer without depending on memory replay.
  arXiv  Detail & Related papers  (2024-08-09T17:44:45Z)
• Interactive Continual Learning: Fast and Slow Thinking [19.253164551254734]
  This paper presents a novel Interactive Continual Learning framework, enabled by collaborative interactions among models of various sizes. To improve memory retrieval in System1, we introduce the CL-vMF mechanism, based on the von Mises-Fisher (vMF) distribution. Comprehensive evaluation of our proposed ICL demonstrates significant resistance to forgetting and superior performance relative to existing methods.
  arXiv  Detail & Related papers  (2024-03-05T03:37:28Z)
• SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models [71.78800549517298]
  Continual learning (CL) ability is vital for deploying large language models (LLMs) in the dynamic world. Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input. We propose a novel Shared Attention Framework (SAPT) to align the PET learning and selection via the Shared Attentive Learning & Selection module.
  arXiv  Detail & Related papers  (2024-01-16T11:45:03Z)
• A Survey on Efficient Federated Learning Methods for Foundation Model Training [62.473245910234304]
  Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. In the wake of Foundation Models (FM), the reality is different for many deep learning applications. We discuss the benefits and drawbacks of parameter-efficient fine-tuning (PEFT) for FL applications.
  arXiv  Detail & Related papers  (2024-01-09T10:22:23Z)
• Federated Continual Learning via Knowledge Fusion: A Survey [33.74289759536269]
  Federated Continual Learning (FCL) is an emerging paradigm to address model learning in both federated and continual learning environments. The key objective of FCL is to fuse heterogeneous knowledge from different clients and retain knowledge of previous tasks while learning on new ones. In this work, we delineate federated learning and continual learning first and then discuss their integration, i.e., FCL, and particular FCL via knowledge fusion.
  arXiv  Detail & Related papers  (2023-12-27T08:47:39Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey [0.6240603866868214]
  Multi-Task Learning (MTL) has emerged as a promising approach to improve efficiency and performance through joint training. We discuss the challenges and opportunities of using MTL approaches throughout typical machine learning lifecycle phases. We believe it would be practical to have a model that can handle both MTL and continual learning.
  arXiv  Detail & Related papers  (2023-08-16T09:11:00Z)
• Learning without Forgetting for Vision-Language Models [65.49600786387106]
  Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world. Recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations. We propose PROjectiOn Fusion (PROOF) that enables VLMs to learn without forgetting.
  arXiv  Detail & Related papers  (2023-05-30T17:59:32Z)
• A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning [54.617688468341704]
  Few-shot learning aims to learn models that generalize to novel classes with limited training samples. We propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data.
  arXiv  Detail & Related papers  (2021-10-21T13:25:52Z)
• ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification [21.933876113300897]
  We adopt an alternative approach by transfer learning on an ensemble of related tasks using prototypical networks under the meta-learning paradigm. Using intent classification as a case study, we demonstrate that increasing variability in training tasks can significantly improve classification performance.
  arXiv  Detail & Related papers  (2021-01-28T00:19:13Z)

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.