InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification

• URL: http://arxiv.org/abs/2109.07319v4
• Date: Fri, 3 May 2024 17:35:02 GMT
• Title: InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification
• Authors: Siddhant Kharbanda, Atmadeep Banerjee, Devaansh Gupta, Akash Palrecha, Rohit Babbar,
• Abstract summary: InceptionXML is light-weight, yet powerful, and robust to the inherent lack of word-order in short-text queries. We show that not only can InceptionXML outperform existing approaches on benchmark datasets but also the transformer baselines requiring only 2% FLOPs.
• Score: 5.637543626451507
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic annotation of short-text data to a large number of target labels, referred to as Short Text Extreme Classification, has found numerous applications including prediction of related searches and product recommendation. In this paper, we propose a convolutional architecture InceptionXML which is light-weight, yet powerful, and robust to the inherent lack of word-order in short-text queries encountered in search and recommendation. We demonstrate the efficacy of applying convolutions by recasting the operation along the embedding dimension instead of the word dimension as applied in conventional CNNs for text classification. Towards scaling our model to datasets with millions of labels, we also propose SyncXML pipeline which improves upon the shortcomings of the recently proposed dynamic hard-negative mining technique for label short-listing by synchronizing the label-shortlister and extreme classifier. SyncXML not only reduces the inference time to half but is also an order of magnitude smaller than state-of-the-art Astec in terms of model size. Through a comprehensive empirical comparison, we show that not only can InceptionXML outperform existing approaches on benchmark datasets but also the transformer baselines requiring only 2% FLOPs. The code for InceptionXML is available at https://github.com/xmc-aalto/inceptionxml.

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)
• REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking [11.374031643273941]
  REXEL is a highly efficient and accurate model for the joint task of document level cIE (DocIE) It is on average 11 times faster than competitive existing approaches in a similar setting. The combination of speed and accuracy makes REXEL an accurate cost-efficient system for extracting structured information at web-scale.
  arXiv  Detail & Related papers  (2024-04-19T11:04:27Z)
• Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels [60.675714333081466]
  Multi-label recognition (MLR) with incomplete labels is very challenging. Recent works strive to explore the image-to-label correspondence in the vision-language model, ie, CLIP, to compensate for insufficient annotations. We advocate remedying the deficiency of label supervision for the MLR with incomplete labels by deriving a structured semantic prior.
  arXiv  Detail & Related papers  (2023-03-23T12:39:20Z)
• CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification [1.6886874648363768]
  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. Recent approaches, such as XR-Transformer and LightXML, leverage a transformer instance to achieve state-of-the-art performance. We propose CascadeXML, an end-to-end multi-resolution learning pipeline, which can harness the multi-layered architecture of a transformer model for attending to different label resolutions with separate feature representations.
  arXiv  Detail & Related papers  (2022-10-29T11:03:23Z)
• Text Summarization with Oracle Expectation [88.39032981994535]
  Extractive summarization produces summaries by identifying and concatenating the most important sentences in a document. Most summarization datasets do not come with gold labels indicating whether document sentences are summary-worthy. We propose a simple yet effective labeling algorithm that creates soft, expectation-based sentence labels.
  arXiv  Detail & Related papers  (2022-09-26T14:10:08Z)
• Exploiting Dynamic and Fine-grained Semantic Scope for Extreme Multi-label Text Classification [12.508006325140949]
  Extreme multi-label text classification (XMTC) refers to the problem of tagging a given text with the most relevant subset of labels from a large label set. Most existing XMTC methods take advantage of fixed label clusters obtained in early stage to balance performance on tail labels and head labels. We propose a novel framework TReaderXML for XMTC, which adopts dynamic and fine-grained semantic scope from teacher knowledge.
  arXiv  Detail & Related papers  (2022-05-24T11:15:35Z)
• 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)
• Group-aware Label Transfer for Domain Adaptive Person Re-identification [179.816105255584]
  Unsupervised Adaptive Domain (UDA) person re-identification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset without any further annotations. Most successful UDA-ReID approaches combine clustering-based pseudo-label prediction with representation learning and perform the two steps in an alternating fashion. We propose a Group-aware Label Transfer (GLT) algorithm, which enables the online interaction and mutual promotion of pseudo-label prediction and representation learning.
  arXiv  Detail & Related papers  (2021-03-23T07:57:39Z)
• MATCH: Metadata-Aware Text Classification in A Large Hierarchy [60.59183151617578]
  MATCH is an end-to-end framework that leverages both metadata and hierarchy information. We propose different ways to regularize the parameters and output probability of each child label by its parents. Experiments on two massive text datasets with large-scale label hierarchies demonstrate the effectiveness of MATCH.
  arXiv  Detail & Related papers  (2021-02-15T05:23:08Z)
• LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification [27.80266694835677]
  Extreme Multi-label text Classification (XMC) is a task of finding the most relevant labels from a large label set. We propose LightXML, which adopts end-to-end training and dynamic negative labels sampling. In experiments, LightXML outperforms state-of-the-art methods in five extreme multi-label datasets.
  arXiv  Detail & Related papers  (2021-01-09T07:04:18Z)

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.