Don't Just Pay Attention, PLANT It: Transfer L2R Models to Fine-tune Attention in Extreme Multi-Label Text Classification

• URL: http://arxiv.org/abs/2410.23066v1
• Date: Wed, 30 Oct 2024 14:41:23 GMT
• Title: Don't Just Pay Attention, PLANT It: Transfer L2R Models to Fine-tune Attention in Extreme Multi-Label Text Classification
• Abstract summary: We introduce PLANT -- Pretrained and Leveraged AtteNTion -- a novel transfer learning strategy for fine-tuning XMTC decoders. PLANT surpasses existing state-of-the-art methods across all metrics on mimicfull, mimicfifty, mimicfour, eurlex, and wikiten datasets. It particularly excels in few-shot scenarios, outperforming previous models specifically designed for few-shot scenarios by over 50 percentage points in F1 scores on mimicrare and by over 36 percentage points on mimicfew.
• Score: 1.6385815610837162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: State-of-the-art Extreme Multi-Label Text Classification (XMTC) models rely heavily on multi-label attention layers to focus on key tokens in input text, but obtaining optimal attention weights is challenging and resource-intensive. To address this, we introduce PLANT -- Pretrained and Leveraged AtteNTion -- a novel transfer learning strategy for fine-tuning XMTC decoders. PLANT surpasses existing state-of-the-art methods across all metrics on mimicfull, mimicfifty, mimicfour, eurlex, and wikiten datasets. It particularly excels in few-shot scenarios, outperforming previous models specifically designed for few-shot scenarios by over 50 percentage points in F1 scores on mimicrare and by over 36 percentage points on mimicfew, demonstrating its superior capability in handling rare codes. PLANT also shows remarkable data efficiency in few-shot scenarios, achieving precision comparable to traditional models with significantly less data. These results are achieved through key technical innovations: leveraging a pretrained Learning-to-Rank model as the planted attention layer, integrating mutual-information gain to enhance attention, introducing an inattention mechanism, and implementing a stateful-decoder to maintain context. Comprehensive ablation studies validate the importance of these contributions in realizing the performance gains.

Related papers

• SinkTrack: Attention Sink based Context Anchoring for Large Language Models [57.87121346197518]
  Large language models (LLMs) suffer from hallucination and context forgetting.<n>SinkTrack treats BOS> as an information anchor and injects key contextual features into its representation.<n>SinkTrack is training-free, plug-and-play, and introduces negligible inference overhead.
  arXiv  Detail & Related papers  (2026-04-11T04:49:11Z)
• Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning [53.398270878295754]
  Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs)<n>We suggest categorizing tokens within each corpus into two parts -- positive and negative tokens -- based on whether they are useful to improve model performance.<n>We conduct experiments on well-established benchmarks, finding that this forgetting mechanism not only improves overall model performance and also facilitate more diverse model responses.
  arXiv  Detail & Related papers  (2025-08-06T11:22:23Z)
• A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention [3.491141037235349]
  Generalized Category Discovery (GCD) aims to classify unlabeled data from both known and unknown categories.<n>Models tend to focus not only on key objects in the image but also on task-irrelevant background regions.<n>We propose Attention Focusing (AF), an adaptive mechanism designed to sharpen the model's focus by pruning non-informative tokens.
  arXiv  Detail & Related papers  (2025-07-18T18:39:16Z)
• The Achilles Heel of AI: Fundamentals of Risk-Aware Training Data for High-Consequence Models [0.0]
  AI systems in high-consequence domains must detect rare, high-impact events while operating under tight resource constraints.<n>Traditional annotation strategies that prioritize label volume over informational value introduce redundancy and noise.<n>This paper introduces smart-sizing, a training data strategy that emphasizes label diversity, model-guided selection, and marginal utility-based stopping.
  arXiv  Detail & Related papers  (2025-05-20T22:57:35Z)
• SMOTExT: SMOTE meets Large Language Models [19.394116388173885]
  We propose a novel technique, SMOTExT, that adapts the idea of Synthetic Minority Over-sampling (SMOTE) to textual data.<n>Our method generates new synthetic examples by interpolating between BERT-based embeddings of two existing examples.<n>In early experiments, training models solely on generated data achieved comparable performance to models trained on the original dataset.
  arXiv  Detail & Related papers  (2025-05-19T17:57:36Z)
• Learning to Attribute with Attention [75.61481181755744]
  We propose treating attention weights of different attention heads as features.<n>This way, we can learn how to effectively leverage attention weights for attribution.<n>Our resulting method, Attribution with Attention (AT2), reliably performs on par with approaches that involve many ablations.
  arXiv  Detail & Related papers  (2025-04-18T15:36:28Z)
• Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need [83.10178754323955]
  Few-shot learning enables models to generalize from only a few labeled examples. We propose the Unbiased Max-Min Embedding Classification (UMMEC) Method, which addresses the key challenges in few-shot learning. Our method significantly improves classification performance with minimal labeled data, advancing the state-of-the-art in annotatedL.
  arXiv  Detail & Related papers  (2025-03-28T07:23:07Z)
• READ: Reinforcement-based Adversarial Learning for Text Classification with Limited Labeled Data [7.152603583363887]
  Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. This paper proposes a method that encapsulates reinforcement learning-based text generation and semi-supervised adversarial learning approaches. Our method READ, Reinforcement-based Adversarial learning, utilizes an unlabeled dataset to generate diverse synthetic text through reinforcement learning.
  arXiv  Detail & Related papers  (2025-01-14T11:39:55Z)
• KNN Transformer with Pyramid Prompts for Few-Shot Learning [52.735070934075736]
  Few-Shot Learning aims to recognize new classes with limited labeled data. Recent studies have attempted to address the challenge of rare samples with textual prompts to modulate visual features.
  arXiv  Detail & Related papers  (2024-10-14T07:39:30Z)
• Improving Image Clustering with Artifacts Attenuation via Inference-Time Attention Engineering [1.8786950286587742]
  As model size increases, high-norm artifacts anomaly appears in the patches of multi-head attention. We propose Inference-Time Attention Engineering (ITAE) which manipulates attention function during inference. ITAE shows improved clustering accuracy on multiple datasets by exhibiting more expressive features in latent space.
  arXiv  Detail & Related papers  (2024-10-07T07:26:10Z)
• Adaptive Masking Enhances Visual Grounding [12.793586888511978]
  We propose IMAGE, Interpretative MAsking with Gaussian radiation modEling, to enhance vocabulary grounding in low-shot learning scenarios. We evaluate the efficacy of our approach on benchmark datasets, including COCO and ODinW, demonstrating its superior performance in zero-shot and few-shot tasks.
  arXiv  Detail & Related papers  (2024-10-04T05:48:02Z)
• MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learning [3.520960737058199]
  We introduce Multimodal Masked Autoenco-Based One-Shot Learning (Mu-MAE) Mu-MAE integrates a multimodal masked autoencoder with a synchronized masking strategy tailored for wearable sensors. It achieves up to an 80.17% accuracy five-way one-shot multimodal classification for classification without the use of additional data.
  arXiv  Detail & Related papers  (2024-08-08T06:16:00Z)
• STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences [2.1139217176397334]
  Self-supervised pretraining methods with masked prediction demonstrate remarkable within-dataset performance in skeleton-based action recognition.<n>Unlike contrastive learning approaches, they do not produce well-separated clusters.<n>We propose Self-supervised Tuning for 3D Action Recognition in Skeleton sequences (STARS)
  arXiv  Detail & Related papers  (2024-07-15T17:35:38Z)
• Learning Positional Attention for Sequential Recommendation [21.193999811562414]
  We introduce novel attention models that directly learn positional relations. Our proposed models, textbfPARec and textbfFPARec, outperform previous self-attention-based approaches.
  arXiv  Detail & Related papers  (2024-07-03T03:42:13Z)
• Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification [6.660834045805309]
  Pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism. We propose integrating two strategies: token pruning and token combining. Experiments with various datasets demonstrate superior performance compared to baseline models.
  arXiv  Detail & Related papers  (2024-06-03T12:51:52Z)
• Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification [62.425462136772666]
  Fine-grained ship classification in remote sensing (RS-FGSC) poses a significant challenge due to the high similarity between classes and the limited availability of labeled data. Recent advancements in large pre-trained Vision-Language Models (VLMs) have demonstrated impressive capabilities in few-shot or zero-shot learning. This study delves into harnessing the potential of VLMs to enhance classification accuracy for unseen ship categories.
  arXiv  Detail & Related papers  (2024-03-13T05:48:58Z)
• SeiT++: Masked Token Modeling Improves Storage-efficient Training [36.95646819348317]
  Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. achieving highly generalizable and high-performing vision models requires expansive datasets, resulting in significant storage requirements. Recent breakthrough by SeiT proposed the use of Vector-Quantized (VQ) feature vectors (i.e., tokens) as network inputs for vision classification. In this paper, we extend SeiT by integrating Masked Token Modeling (MTM) for self-supervised pre-training.
  arXiv  Detail & Related papers  (2023-12-15T04:11:34Z)
• Retrieval-Enhanced Contrastive Vision-Text Models [61.783728119255365]
  We propose to equip vision-text models with the ability to refine their embedding with cross-modal retrieved information from a memory at inference time. Remarkably, we show that this can be done with a light-weight, single-layer, fusion transformer on top of a frozen CLIP. Our experiments validate that our retrieval-enhanced contrastive (RECO) training improves CLIP performance substantially on several challenging fine-grained tasks.
  arXiv  Detail & Related papers  (2023-06-12T15:52:02Z)
• Three ways to improve feature alignment for open vocabulary detection [88.65076922242184]
  Key problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes. Previous approaches train the feature pyramid and detection head from scratch, which breaks the vision-text feature alignment established during pretraining. We propose three methods to alleviate these issues. Firstly, a simple scheme is used to augment the text embeddings which prevents overfitting to a small number of classes seen during training. Secondly, the feature pyramid network and the detection head are modified to include trainable shortcuts. Finally, a self-training approach is used to leverage a larger corpus of
  arXiv  Detail & Related papers  (2023-03-23T17:59:53Z)
• Large-Scale Pre-training for Person Re-identification with Noisy Labels [125.49696935852634]
  We develop a large-scale Pre-training framework utilizing Noisy Labels (PNL) In principle, joint learning of these three modules not only clusters similar examples to one prototype, but also rectifies noisy labels based on the prototype assignment. This simple pre-training task provides a scalable way to learn SOTA Re-ID representations from scratch on "LUPerson-NL" without bells and whistles.
  arXiv  Detail & Related papers  (2022-03-30T17:59:58Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Learning to ignore: rethinking attention in CNNs [87.01305532842878]
  We propose to reformulate the attention mechanism in CNNs to learn to ignore instead of learning to attend. Specifically, we propose to explicitly learn irrelevant information in the scene and suppress it in the produced representation.
  arXiv  Detail & Related papers  (2021-11-10T13:47:37Z)
• How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction [66.09605613944201]
  We quantitatively evaluate the effect of attention and Knowledge Graph on bag-level relation extraction (RE) We find that (1) higher attention accuracy may lead to worse performance as it may harm the model's ability to extract entity mention features; (2) the performance of attention is largely influenced by various noise distribution patterns; and (3) KG-enhanced attention indeed improves RE performance, while not through enhanced attention but by incorporating entity prior.
  arXiv  Detail & Related papers  (2021-07-26T09:38:28Z)
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption [72.35532598131176]
  We propose SCARF, a technique for contrastive learning, where views are formed by corrupting a random subset of features. We show that SCARF complements existing strategies and outperforms alternatives like autoencoders.
  arXiv  Detail & Related papers  (2021-06-29T08:08:33Z)
• Semi-supervised Left Atrium Segmentation with Mutual Consistency Training [60.59108570938163]
  We propose a novel Mutual Consistency Network (MC-Net) for semi-supervised left atrium segmentation from 3D MR images. Our MC-Net consists of one encoder and two slightly different decoders, and the prediction discrepancies of two decoders are transformed as an unsupervised loss. We evaluate our MC-Net on the public Left Atrium (LA) database and it obtains impressive performance gains by exploiting the unlabeled data effectively.
  arXiv  Detail & Related papers  (2021-03-04T09:34:32Z)
• A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification [65.18004601366066]
  Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
  arXiv  Detail & Related papers  (2020-09-05T16:06:04Z)

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.