Multitask Fine-Tuning and Generative Adversarial Learning for Improved Auxiliary Classification

• URL: http://arxiv.org/abs/2408.15265v1
• Date: Sun, 11 Aug 2024 20:05:54 GMT
• Title: Multitask Fine-Tuning and Generative Adversarial Learning for Improved Auxiliary Classification
• Authors: Christopher Sun, Abishek Satish,
• Abstract summary: We implement a novel BERT architecture for multitask fine-tuning on three downstream tasks. Our model, Multitask BERT, incorporates layer sharing and a triplet architecture, custom sentence pair tokenization, loss pairing, and gradient surgery. We also apply generative adversarial learning to BERT, constructing a conditional generator model that maps from latent space to create fake embeddings.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this study, we implement a novel BERT architecture for multitask fine-tuning on three downstream tasks: sentiment classification, paraphrase detection, and semantic textual similarity prediction. Our model, Multitask BERT, incorporates layer sharing and a triplet architecture, custom sentence pair tokenization, loss pairing, and gradient surgery. Such optimizations yield a 0.516 sentiment classification accuracy, 0.886 paraphase detection accuracy, and 0.864 semantic textual similarity correlation on test data. We also apply generative adversarial learning to BERT, constructing a conditional generator model that maps from latent space to create fake embeddings in $\mathbb{R}^{768}$. These fake embeddings are concatenated with real BERT embeddings and passed into a discriminator model for auxiliary classification. Using this framework, which we refer to as AC-GAN-BERT, we conduct semi-supervised sensitivity analyses to investigate the effect of increasing amounts of unlabeled training data on AC-GAN-BERT's test accuracy. Overall, aside from implementing a high-performing multitask classification system, our novelty lies in the application of adversarial learning to construct a generator that mimics BERT. We find that the conditional generator successfully produces rich embeddings with clear spatial correlation with class labels, demonstrating avoidance of mode collapse. Our findings validate the GAN-BERT approach and point to future directions of generator-aided knowledge distillation.

Related papers

• BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation [4.977568882858193]
  Scene Graph Generation (SGG) remains a challenging task due to its compositional property. Previous approaches improve prediction efficiency by learning in an end-to-end manner. We propose a novel bidirectional conditioning factorization for SGG, introducing efficient interaction between entities and predicates.
  arXiv  Detail & Related papers  (2024-07-26T13:02:48Z)
• Downstream-Pretext Domain Knowledge Traceback for Active Learning [138.02530777915362]
  We propose a downstream-pretext domain knowledge traceback (DOKT) method that traces the data interactions of downstream knowledge and pre-training guidance. DOKT consists of a traceback diversity indicator and a domain-based uncertainty estimator. Experiments conducted on ten datasets show that our model outperforms other state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-20T01:34:13Z)
• A Diffusion Weighted Graph Framework for New Intent Discovery [25.364554033681515]
  New Intent Discovery (NID) aims to recognize both new and known intents from unlabeled data. Previous methods generate noisy supervisory signals which cannot strike a balance between quantity and quality. We propose a novel Diffusion Weighted Graph Framework (DWGF) to capture both semantic similarities and structure relationships inherent in data.
  arXiv  Detail & Related papers  (2023-10-24T13:43:01Z)
• Threshold-Consistent Margin Loss for Open-World Deep Metric Learning [42.03620337000911]
  Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures. Inconsistency often complicates the threshold selection process when deploying commercial image retrieval systems. We propose a novel variance-based metric called Operating-Point-Inconsistency-Score (OPIS) that quantifies the variance in the operating characteristics across classes.
  arXiv  Detail & Related papers  (2023-07-08T21:16:41Z)
• ProTeCt: Prompt Tuning for Taxonomic Open Set Classification [59.59442518849203]
  Few-shot adaptation methods do not fare well in the taxonomic open set (TOS) setting. We propose a prompt tuning technique that calibrates the hierarchical consistency of model predictions. A new Prompt Tuning for Hierarchical Consistency (ProTeCt) technique is then proposed to calibrate classification across label set granularities.
  arXiv  Detail & Related papers  (2023-06-04T02:55:25Z)
• Pretraining Without Attention [114.99187017618408]
  This work explores pretraining without attention by using recent advances in sequence routing based on state-space models (SSMs) BiGS is able to match BERT pretraining accuracy on GLUE and can be extended to long-form pretraining of 4096 tokens without approximation.
  arXiv  Detail & Related papers  (2022-12-20T18:50:08Z)
• Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation [30.34223543030105]
  We show how NeighborAgg can leverage the two essential information via an adaptive neighborhood aggregation. We also extend our approach to the closely related task of mislabel detection and provide a theoretical coverage guarantee to bound the false negative.
  arXiv  Detail & Related papers  (2022-11-29T18:43:15Z)
• Hybrid Routing Transformer for Zero-Shot Learning [83.64532548391]
  This paper presents a novel transformer encoder-decoder model, called hybrid routing transformer (HRT) We embed an active attention, which is constructed by both the bottom-up and the top-down dynamic routing pathways to generate the attribute-aligned visual feature. While in HRT decoder, we use static routing to calculate the correlation among the attribute-aligned visual features, the corresponding attribute semantics, and the class attribute vectors to generate the final class label predictions.
  arXiv  Detail & Related papers  (2022-03-29T07:55:08Z)
• Diversity Enhanced Active Learning with Strictly Proper Scoring Rules [4.81450893955064]
  We study acquisition functions for active learning (AL) for text classification. We convert the Expected Loss Reduction (ELR) method to estimate the increase in (strictly proper) scores like log probability or negative mean square error. We show that the use of mean square error and log probability with BEMPS yields robust acquisition functions.
  arXiv  Detail & Related papers  (2021-10-27T05:02:11Z)
• Mitigating Generation Shifts for Generalized Zero-Shot Learning [52.98182124310114]
  Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. We propose a novel Generation Shifts Mitigating Flow framework for learning unseen data synthesis efficiently and effectively. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings.
  arXiv  Detail & Related papers  (2021-07-07T11:43:59Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)

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.