CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification

• URL: http://arxiv.org/abs/2211.00640v1
• Date: Sat, 29 Oct 2022 11:03:23 GMT
• Title: CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification
• Authors: Siddhant Kharbanda and Atmadeep Banerjee and Erik Schultheis and Rohit Babbar
• Abstract summary: 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.
• Score: 1.6886874648363768
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. However, in this process, these approaches need to make various trade-offs between performance and computational requirements. A major shortcoming, as compared to the Bi-LSTM based AttentionXML, is that they fail to keep separate feature representations for each resolution in a label tree. We thus 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. CascadeXML significantly outperforms all existing approaches with non-trivial gains obtained on benchmark datasets consisting of up to three million labels. Code for CascadeXML will be made publicly available at \url{https://github.com/xmc-aalto/cascadexml}.

Related papers

• 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)
• Light-weight Deep Extreme Multilabel Classification [12.29534534973133]
  Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels. We develop a method called LightDXML which modifies the recently developed deep learning based XML framework by using label embeddings. LightDXML also removes the requirement of a re-ranker module, thereby, leading to further savings on time and memory requirements.
  arXiv  Detail & Related papers  (2023-04-20T09:06:10Z)
• A Survey on Extreme Multi-label Learning [72.8751573611815]
  Multi-label learning has attracted significant attention from both academic and industry field in recent decades. It is infeasible to directly adapt them to extremely large label space because of the compute and memory overhead. eXtreme Multi-label Learning (XML) is becoming an important task and many effective approaches are proposed.
  arXiv  Detail & Related papers  (2022-10-08T08:31:34Z)
• Large Loss Matters in Weakly Supervised Multi-Label Classification [50.262533546999045]
  We first regard unobserved labels as negative labels, casting the W task into noisy multi-label classification. We propose novel methods for W which reject or correct the large loss samples to prevent model from memorizing the noisy label. Our methodology actually works well, validating that treating large loss properly matters in a weakly supervised multi-label classification.
  arXiv  Detail & Related papers  (2022-06-08T08:30:24Z)
• Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels [86.17081952197788]
  We propose to blend category-specific representation across different images to transfer information of known labels to complement unknown labels. Experiments on the MS-COCO, Visual Genome, Pascal VOC 2007 datasets show that the proposed SARB framework obtains superior performance over current leading competitors.
  arXiv  Detail & Related papers  (2022-03-04T07:56:16Z)
• 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)
• InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification [5.637543626451507]
  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.
  arXiv  Detail & Related papers  (2021-09-13T18:55:37Z)
• 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)
• 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)
• 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)

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.