Retrieval-augmented Encoders for Extreme Multi-label Text Classification

• URL: http://arxiv.org/abs/2502.10615v1
• Date: Sat, 15 Feb 2025 00:30:28 GMT
• Title: Retrieval-augmented Encoders for Extreme Multi-label Text Classification
• Authors: Yau-Shian Wang, Wei-Cheng Chang, Jyun-Yu Jiang, Jiong Zhang, Hsiang-Fu Yu, S. V. N. Vishwanathan,
• Abstract summary: Extreme multi-label classification (XMC) seeks to find relevant labels from an extremely large label collection for a given text input. The one-versus-all (OVA) method uses learnable label embeddings for each label, excelling at memorization. The dual-encoder (DE) model maps input and label text into a shared embedding space for better generalization.
• Score: 31.300502762878914
• License:
• Abstract: Extreme multi-label classification (XMC) seeks to find relevant labels from an extremely large label collection for a given text input. To tackle such a vast label space, current state-of-the-art methods fall into two categories. The one-versus-all (OVA) method uses learnable label embeddings for each label, excelling at memorization (i.e., capturing detailed training signals for accurate head label prediction). In contrast, the dual-encoder (DE) model maps input and label text into a shared embedding space for better generalization (i.e., the capability of predicting tail labels with limited training data), but may fall short at memorization. To achieve generalization and memorization, existing XMC methods often combine DE and OVA models, which involves complex training pipelines. Inspired by the success of retrieval-augmented language models, we propose the Retrieval-augmented Encoders for XMC (RAEXMC), a novel framework that equips a DE model with retrieval-augmented capability for efficient memorization without additional trainable parameter. During training, RAEXMC is optimized by the contrastive loss over a knowledge memory that consists of both input instances and labels. During inference, given a test input, RAEXMC retrieves the top-$K$ keys from the knowledge memory, and aggregates the corresponding values as the prediction scores. We showcase the effectiveness and efficiency of RAEXMC on four public LF-XMC benchmarks. RAEXMC not only advances the state-of-the-art (SOTA) DE method DEXML, but also achieves more than 10x speedup on the largest LF-AmazonTitles-1.3M dataset under the same 8 A100 GPUs training environments.

Related papers

• Prototypical Extreme Multi-label Classification with a Dynamic Margin Loss [6.244642999033755]
  Extreme Multi-label Classification (XMC) methods predict relevant labels for a given query in an extremely large label space. Recent works in XMC address this problem using deep encoders that project text descriptions to an embedding space suitable for recovering the closest labels. We propose PRIME, a XMC method that employs a novel prototypical contrastive learning technique to reconcile efficiency and performance surpassing brute-force approaches.
  arXiv  Detail & Related papers  (2024-10-27T10:24:23Z)
• Zero-Shot Learning Over Large Output Spaces : Utilizing Indirect Knowledge Extraction from Large Language Models [3.908992369351976]
  Extreme Zero-shot XMC (EZ-XMC) is a special setting of XMC wherein no supervision is provided. Traditional state-of-the-art methods extract pseudo labels from the document title or segments. We propose a framework to train a small bi-encoder model via the feedback from the large language model (LLM)
  arXiv  Detail & Related papers  (2024-06-13T16:26:37Z)
• UniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification [42.36546066941635]
  Extreme Multi-label Classification (XMC) involves predicting a subset of relevant labels from an extremely large label space. This work proposes UniDEC, a novel end-to-end trainable framework which trains the dual encoder and classifier in together.
  arXiv  Detail & Related papers  (2024-05-04T17:27:51Z)
• Learning label-label correlations in Extreme Multi-label Classification via Label Features [44.00852282861121]
  Extreme Multi-label Text Classification (XMC) involves learning a classifier that can assign an input with a subset of most relevant labels from millions of label choices. Short-text XMC with label features has found numerous applications in areas such as query-to-ad-phrase matching in search ads, title-based product recommendation, prediction of related searches. We propose Gandalf, a novel approach which makes use of a label co-occurrence graph to leverage label features as additional data points to supplement the training distribution.
  arXiv  Detail & Related papers  (2024-05-03T21:18:43Z)
• PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation [105.52660004082766]
  The eXtreme Multi-label Classification(XMC) problem seeks to find relevant labels from an exceptionally large label space. We propose Predicted Instance Neighborhood Aggregation (PINA), a data enhancement method for the general XMC problem. Unlike most existing XMC frameworks that treat labels and input instances as featureless indicators and independent entries, PINA extracts information from the label metadata and the correlations among training instances.
  arXiv  Detail & Related papers  (2023-05-21T05:00:40Z)
• One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement [71.9401831465908]
  We investigate single-positive multi-label learning (SPMLL) where each example is annotated with only one relevant label. A novel method named proposed, i.e., Single-positive MultI-label learning with Label Enhancement, is proposed. Experiments on benchmark datasets validate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-06-01T14:26:30Z)
• Extreme Zero-Shot Learning for Extreme Text Classification [80.95271050744624]
  Extreme Zero-Shot XMC (EZ-XMC) and Few-Shot XMC (FS-XMC) are investigated. We propose to pre-train Transformer-based encoders with self-supervised contrastive losses. We develop a pre-training method MACLR, which thoroughly leverages the raw text with techniques including Multi-scale Adaptive Clustering, Label Regularization, and self-training with pseudo positive pairs.
  arXiv  Detail & Related papers  (2021-12-16T06:06:42Z)
• Label Disentanglement in Partition-based Extreme Multilabel Classification [111.25321342479491]
  We show that the label assignment problem in partition-based XMC can be formulated as an optimization problem. We show that our method can successfully disentangle multi-modal labels, leading to state-of-the-art (SOTA) results on four XMC benchmarks.
  arXiv  Detail & Related papers  (2021-06-24T03:24:18Z)
• HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization [75.45291796263103]
  The current state-of-the-art model HiAGM for hierarchical text classification has two limitations. It correlates each text sample with all labels in the dataset which contains irrelevant information. We propose HTCInfoMax to address these issues by introducing information which includes two modules.
  arXiv  Detail & Related papers  (2021-04-12T06:04:20Z)

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.