Constructing Enhanced Mutual Information for Online Class-Incremental Learning

• URL: http://arxiv.org/abs/2407.18526v1
• Date: Fri, 26 Jul 2024 06:16:11 GMT
• Title: Constructing Enhanced Mutual Information for Online Class-Incremental Learning
• Authors: Huan Zhang, Fan Lyu, Shenghua Fan, Yujin Zheng, Dingwen Wang,
• Abstract summary: Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream. Existing Mutual Information (MI)-based methods treat various knowledge components in isolation, ignoring the knowledge confusion across tasks. We propose an Enhanced Mutual Information (EMI) method based on knwoledge decoupling.
• Score: 11.555090963348595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online Class-Incremental continual Learning (OCIL) addresses the challenge of continuously learning from a single-channel data stream, adapting to new tasks while mitigating catastrophic forgetting. Recently, Mutual Information (MI)-based methods have shown promising performance in OCIL. However, existing MI-based methods treat various knowledge components in isolation, ignoring the knowledge confusion across tasks. This narrow focus on simple MI knowledge alignment may lead to old tasks being easily forgotten with the introduction of new tasks, risking the loss of common parts between past and present knowledge.To address this, we analyze the MI relationships from the perspectives of diversity, representativeness, and separability, and propose an Enhanced Mutual Information (EMI) method based on knwoledge decoupling. EMI consists of Diversity Mutual Information (DMI), Representativeness Mutual Information (RMI) and Separability Mutual Information (SMI). DMI diversifies intra-class sample features by considering the similarity relationships among inter-class sample features to enable the network to learn more general knowledge. RMI summarizes representative features for each category and aligns sample features with these representative features, making the intra-class sample distribution more compact. SMI establishes MI relationships for inter-class representative features, enhancing the stability of representative features while increasing the distinction between inter-class representative features, thus creating clear boundaries between class. Extensive experimental results on widely used benchmark datasets demonstrate the superior performance of EMI over state-of-the-art baseline methods.

Related papers

• From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation [59.27094165576015]
  We propose a novel learning paradigm (UniMod) that transitions from sparse decision-making to dense reasoning traces.<n>By constructing structured trajectories encompassing evidence grounding, modality assessment, risk mapping, policy decision, and response generation, we reformulate monolithic decision tasks into a multi-dimensional boundary learning process.<n>We introduce specialized optimization strategies to decouple task-specific parameters and rebalance training dynamics, effectively resolving interference between diverse objectives in multi-task learning.
  arXiv  Detail & Related papers  (2026-01-28T09:29:40Z)
• Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations [0.0]
  We introduce the contrastive Mutual Information Machine (cMIM), a probabilistic framework that extends the Mutual Information Machine (MIM) with a contrastive objective.<n>CMIM addresses this gap by imposing global discriminative structure while retaining MIM's generative fidelity.<n>We provide empirical evidence across vision and molecular benchmarks showing that cMIM outperforms MIM and InfoNCE on classification and regression tasks.
  arXiv  Detail & Related papers  (2025-09-25T20:03:24Z)
• cMIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning [0.0]
  We introduce contrastive Mutual Information Machine (cMIM), which aims to enhance the utility of learned representations for downstream tasks. Initial experiments indicated that the representations learned by MIM were less effective for discriminative downstream tasks compared to state-of-the-art (SOTA) models. We introduce a generic method for extracting informative embeddings from encoder-decoder models, which significantly improves performance in discriminative downstream tasks without requiring additional training.
  arXiv  Detail & Related papers  (2025-02-27T00:23:40Z)
• Detecting Training Data of Large Language Models via Expectation Maximization [62.28028046993391]
  Membership inference attacks (MIAs) aim to determine whether a specific instance was part of a target model's training data. Applying MIAs to large language models (LLMs) presents unique challenges due to the massive scale of pre-training data and the ambiguous nature of membership. We introduce EM-MIA, a novel MIA method for LLMs that iteratively refines membership scores and prefix scores via an expectation-maximization algorithm.
  arXiv  Detail & Related papers  (2024-10-10T03:31:16Z)
• Detached and Interactive Multimodal Learning [17.843121072628477]
  This paper introduces DI-MML, a novel detached MML framework designed to learn complementary information across modalities. It addresses competition by separately training each modality encoder with isolated learning objectives. Experiments conducted on audio-visual, flow-image, and front-rear view datasets show the superior performance of our proposed method.
  arXiv  Detail & Related papers  (2024-07-28T15:38:58Z)
• POGEMA: A Benchmark Platform for Cooperative Multi-Agent Navigation [76.67608003501479]
  We introduce and specify an evaluation protocol defining a range of domain-related metrics computed on the basics of the primary evaluation indicators. The results of such a comparison, which involves a variety of state-of-the-art MARL, search-based, and hybrid methods, are presented.
  arXiv  Detail & Related papers  (2024-07-20T16:37:21Z)
• Completed Feature Disentanglement Learning for Multimodal MRIs Analysis [36.32164729310868]
  Feature disentanglement (FD)-based methods have achieved significant success in multimodal learning (MML) We propose a novel Complete Feature Disentanglement (CFD) strategy that recovers the lost information during feature decoupling. Specifically, the CFD strategy not only identifies modality-shared and modality-specific features, but also decouples shared features among subsets of multimodal inputs.
  arXiv  Detail & Related papers  (2024-07-06T01:49:38Z)
• 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)
• Constrained Multiview Representation for Self-supervised Contrastive Learning [4.817827522417457]
  We introduce a novel approach predicated on representation distance-based mutual information (MI) for measuring the significance of different views. We harness multi-view representations extracted from the frequency domain, re-evaluating their significance based on mutual information.
  arXiv  Detail & Related papers  (2024-02-05T19:09:33Z)
• Knowledge-Enhanced Hierarchical Information Correlation Learning for Multi-Modal Rumor Detection [82.94413676131545]
  We propose a novel knowledge-enhanced hierarchical information correlation learning approach (KhiCL) for multi-modal rumor detection. KhiCL exploits cross-modal joint dictionary to transfer the heterogeneous unimodality features into the common feature space. It extracts visual and textual entities from images and text, and designs a knowledge relevance reasoning strategy.
  arXiv  Detail & Related papers  (2023-06-28T06:08:20Z)
• Diffeomorphic Information Neural Estimation [2.566492438263125]
  Mutual Information (MI) and Conditional Mutual Information (CMI) are multi-purpose tools from information theory. We introduce DINE (Diffeomorphic Information Neural Estorimator)-a novel approach for estimating CMI of continuous random variables. We show that the variables of interest can be replaced with appropriate surrogates that follow simpler distributions.
  arXiv  Detail & Related papers  (2022-11-20T03:03:56Z)
• Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing [73.29587731448345]
  We propose a novel method, dubbed Cross-Modal Info-Max Hashing (CMIMH) We learn informative representations that can preserve both intra- and inter-modal similarities. The proposed method consistently outperforms other state-of-the-art cross-modal retrieval methods.
  arXiv  Detail & Related papers  (2021-12-13T08:58:03Z)
• Learning Multimodal VAEs through Mutual Supervision [72.77685889312889]
  MEME combines information between modalities implicitly through mutual supervision. We demonstrate that MEME outperforms baselines on standard metrics across both partial and complete observation schemes.
  arXiv  Detail & Related papers  (2021-06-23T17:54:35Z)
• Memory-Augmented Relation Network for Few-Shot Learning [114.47866281436829]
  In this work, we investigate a new metric-learning method, Memory-Augmented Relation Network (MRN) In MRN, we choose the samples that are visually similar from the working context, and perform weighted information propagation to attentively aggregate helpful information from chosen ones to enhance its representation. We empirically demonstrate that MRN yields significant improvement over its ancestor and achieves competitive or even better performance when compared with other few-shot learning approaches.
  arXiv  Detail & Related papers  (2020-05-09T10:09:13Z)
• Mutual Information Gradient Estimation for Representation Learning [56.08429809658762]
  Mutual Information (MI) plays an important role in representation learning. Recent advances establish tractable and scalable MI estimators to discover useful representation. We propose the Mutual Information Gradient Estimator (MIGE) for representation learning based on the score estimation of implicit distributions.
  arXiv  Detail & Related papers  (2020-05-03T16:05:58Z)

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.