Rethinking Label-specific Features for Label Distribution Learning

• URL: http://arxiv.org/abs/2504.19374v1
• Date: Sun, 27 Apr 2025 22:32:46 GMT
• Title: Rethinking Label-specific Features for Label Distribution Learning
• Authors: Suping Xu, Chuyi Dai, Lin Shang, Changbin Shao, Xibei Yang, Witold Pedrycz,
• Abstract summary: Label-specific features (LSFs) have proven effective for learning tasks with label ambiguity by leveraging clustering-based prototypes for each label.<n>We propose a novel LDL algorithm, Label Distribution Learning via Label-specifIc FeaTure with SAPs (LDL-LIFT-SAP), which unifies multiple label description degrees predicted from different LSF spaces into a cohesive label distribution.
• Score: 42.463322504410336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label distribution learning (LDL) is an emerging learning paradigm designed to capture the relative importance of labels for each instance. Label-specific features (LSFs), constructed by LIFT, have proven effective for learning tasks with label ambiguity by leveraging clustering-based prototypes for each label to re-characterize instances. However, directly introducing LIFT into LDL tasks can be suboptimal, as the prototypes it collects primarily reflect intra-cluster relationships while neglecting interactions among distinct clusters. Additionally, constructing LSFs using multi-perspective information, rather than relying solely on Euclidean distance, provides a more robust and comprehensive representation of instances, mitigating noise and bias that may arise from a single distance perspective. To address these limitations, we introduce Structural Anchor Points (SAPs) to capture inter-cluster interactions. This leads to a novel LSFs construction strategy, LIFT-SAP, which enhances LIFT by integrating both distance and direction information of each instance relative to SAPs. Furthermore, we propose a novel LDL algorithm, Label Distribution Learning via Label-specifIc FeaTure with SAPs (LDL-LIFT-SAP), which unifies multiple label description degrees predicted from different LSF spaces into a cohesive label distribution. Extensive experiments on 15 real-world datasets demonstrate the effectiveness of LIFT-SAP over LIFT, as well as the superiority of LDL-LIFT-SAP compared to seven other well-established algorithms.

Related papers

• Incremental Label Distribution Learning with Scalable Graph Convolutional Networks [41.02170058889797]
  We introduce Incremental Label Distribution Learning (ILDL), analyze its key issues regarding training samples and inter-label relationships. Specifically, we develop a New-label-aware Gradient Compensation Loss to speed up the learning of new labels and represent inter-label relationships as a graph.
  arXiv  Detail & Related papers  (2024-11-20T07:49:51Z)
• Towards Better Performance in Incomplete LDL: Addressing Data Imbalance [48.54894491724677]
  We propose textIncomplete and Imbalance Label Distribution Learning (I(2)LDL), a framework that simultaneously handles incomplete labels and imbalanced label distributions. Our method decomposes the label distribution matrix into a low-rank component for frequent labels and a sparse component for rare labels, effectively capturing the structure of both head and tail labels.
  arXiv  Detail & Related papers  (2024-10-17T14:12:57Z)
• RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations [52.549807652527306]
  This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL) RankMatch effectively utilizes a small number of labeled examples in conjunction with a larger quantity of unlabeled data. We establish a theoretical generalization bound for RankMatch, and through extensive experiments, demonstrate its superiority in performance against existing SSLDL methods.
  arXiv  Detail & Related papers  (2023-12-11T12:47:29Z)
• Scalable Label Distribution Learning for Multi-Label Classification [43.52928088881866]
  Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels. Most existing MLC methods are based on the assumption that the correlation of two labels in each label pair is symmetric. Most existing methods design learning processes associated with the number of labels, which makes their computational complexity a bottleneck when scaling up to large-scale output space.
  arXiv  Detail & Related papers  (2023-11-28T06:52:53Z)
• FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning [70.38817963253034]
  This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution. We provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings.
  arXiv  Detail & Related papers  (2023-09-01T09:40:36Z)
• Robust Representation Learning for Unreliable Partial Label Learning [86.909511808373]
  Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth. This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels. We propose the Unreliability-Robust Representation Learning framework (URRL) that leverages unreliability-robust contrastive learning to help the model fortify against unreliable partial labels effectively.
  arXiv  Detail & Related papers  (2023-08-31T13:37:28Z)
• Contrastive Label Enhancement [13.628665406039609]
  We propose Contrastive Label Enhancement (ConLE) to generate high-level features by contrastive learning strategy. We leverage the obtained high-level features to gain label distributions through a welldesigned training strategy.
  arXiv  Detail & Related papers  (2023-05-16T14:53:07Z)
• Label Distribution Learning from Logical Label [19.632157794117553]
  Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. But annotating label distribution for training samples is extremely costly. We propose a novel method to learn an LDL model directly from the logical label, which unifies LE and LDL into a joint model.
  arXiv  Detail & Related papers  (2023-03-13T04:31:35Z)
• An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels [49.036212158261215]
  Large-scale Multi-label Text Classification (LMTC) has a wide range of Natural Language Processing (NLP) applications. Current state-of-the-art LMTC models employ Label-Wise Attention Networks (LWANs) We show that hierarchical methods based on Probabilistic Label Trees (PLTs) outperform LWANs. We propose a new state-of-the-art method which combines BERT with LWANs.
  arXiv  Detail & Related papers  (2020-10-04T18:55:47Z)
• Generalized Label Enhancement with Sample Correlations [24.582764493585362]
  We propose two novel label enhancement methods, i.e., Label Enhancement with Sample Correlations (LESC) and generalized Label Enhancement with Sample Correlations (gLESC) Benefitting from the sample correlations, the proposed methods can boost the performance of label enhancement.
  arXiv  Detail & Related papers  (2020-04-07T03:32:36Z)
• Partial Multi-label Learning with Label and Feature Collaboration [21.294791188490056]
  Partial multi-label learning (PML) models the scenario where each training instance is annotated with a set of candidate labels. To achieve a credible predictor on PML data, we propose PML-LFC (Partial Multi-label Learning with Label and Feature Collaboration) PML-LFC estimates the confidence values of relevant labels for each instance using the similarity from both the label and feature spaces.
  arXiv  Detail & Related papers  (2020-03-17T08:34:45Z)

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.