Bidirectional Awareness Induction in Autoregressive Seq2Seq Models
- URL: http://arxiv.org/abs/2408.13959v1
- Date: Sun, 25 Aug 2024 23:46:35 GMT
- Title: Bidirectional Awareness Induction in Autoregressive Seq2Seq Models
- Authors: Jia Cheng Hu, Roberto Cavicchioli, Alessandro Capotondi,
- Abstract summary: Bidirectional Awareness Induction (BAI) is a training method that leverages a subset of elements in the network, the Pivots, to perform bidirectional learning without breaking the autoregressive constraints.
In particular, we observed an increase of up to 2.4 CIDEr in Image-Captioning, 4.96 BLEU in Neural Machine Translation, and 1.16 ROUGE in Text Summarization compared to the respective baselines.
- Score: 47.82947878753809
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Autoregressive Sequence-To-Sequence models are the foundation of many Deep Learning achievements in major research fields such as Vision and Natural Language Processing. Despite that, they still present significant limitations. For instance, when errors occur in the early steps of the prediction, the whole output is severely affected. Such reliance on previously predicted tokens and the inherent computational unfriendliness of sequential algorithms, motivated researchers to explore different architectures and methods in the search for bidirectional approaches. In this work, we introduce the Bidirectional Awareness Induction (BAI), a training method that leverages a subset of elements in the network, the Pivots, to perform bidirectional learning without breaking the autoregressive constraints. To showcase its flexibility, we apply the method to three architectures, the Transformer, ExpansionNet v2 and GPT, then perform experiments over three tasks. Experimental results showcase BAI's effectiveness on all selected tasks and architectures. In particular, we observed an increase of up to 2.4 CIDEr in Image-Captioning, 4.96 BLEU in Neural Machine Translation, and 1.16 ROUGE in Text Summarization compared to the respective baselines. Notably, BAI not only has a positive impact on models trained from scratch but on pre-trained models as well. Such an aspect, combined with the absence of architectural requirements synergizes well with the current trend of LLMs.
Related papers
- SMLE: Safe Machine Learning via Embedded Overapproximation [4.129133569151574]
We consider the task of training differentiable ML models guaranteed to satisfy designer-chosen properties.
This is very challenging, due to the computational complexity of rigorously verifying and enforcing compliance in modern neural models.
We provide an innovative approach based on three components: 1) a general, simple architecture enabling efficient verification with a conservative semantic.
We evaluate our approach on properties defined by linear inequalities in regression, and on mutually exclusive classes in multilabel classification.
arXiv Detail & Related papers (2024-09-30T17:19:57Z) - Visual Prompt Tuning in Null Space for Continual Learning [51.96411454304625]
Existing prompt-tuning methods have demonstrated impressive performances in continual learning (CL)
This paper aims to learn each task by tuning the prompts in the direction orthogonal to the subspace spanned by previous tasks' features.
In practice, an effective null-space-based approximation solution has been proposed to implement the prompt gradient projection.
arXiv Detail & Related papers (2024-06-09T05:57:40Z) - In-Context Language Learning: Architectures and Algorithms [73.93205821154605]
We study ICL through the lens of a new family of model problems we term in context language learning (ICLL)
We evaluate a diverse set of neural sequence models on regular ICLL tasks.
arXiv Detail & Related papers (2024-01-23T18:59:21Z) - Robust Graph Representation Learning via Predictive Coding [46.22695915912123]
Predictive coding is a message-passing framework initially developed to model information processing in the brain.
In this work, we build models that rely on the message-passing rule of predictive coding.
We show that the proposed models are comparable to standard ones in terms of performance in both inductive and transductive tasks.
arXiv Detail & Related papers (2022-12-09T03:58:22Z) - SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video
Anomaly Detection [108.57862846523858]
We revisit the self-supervised multi-task learning framework, proposing several updates to the original method.
We modernize the 3D convolutional backbone by introducing multi-head self-attention modules.
In our attempt to further improve the model, we study additional self-supervised learning tasks, such as predicting segmentation maps.
arXiv Detail & Related papers (2022-07-16T19:25:41Z) - On the Role of Bidirectionality in Language Model Pre-Training [85.14614350372004]
We study the role of bidirectionality in next token prediction, text infilling, zero-shot priming and fine-tuning.
We train models with up to 6.7B parameters, and find differences to remain consistent at scale.
arXiv Detail & Related papers (2022-05-24T02:25:05Z) - Inducing Causal Structure for Interpretable Neural Networks [23.68246698789134]
We present the new method of interchange intervention training(IIT)
In IIT, we (1)align variables in the causal model with representations in the neural model and (2) train a neural model to match the counterfactual behavior of the causal model on a base input.
IIT is fully differentiable, flexibly combines with other objectives, and guarantees that the target causal model is acausal abstraction of the neural model.
arXiv Detail & Related papers (2021-12-01T21:07:01Z) - Lipreading using Temporal Convolutional Networks [57.41253104365274]
Current model for recognition of isolated words in-the-wild consists of a residual network and Bi-directional Gated Recurrent Unit layers.
We address the limitations of this model and we propose changes which further improve its performance.
Our proposed model results in an absolute improvement of 1.2% and 3.2%, respectively, in these datasets.
arXiv Detail & Related papers (2020-01-23T17:49:35Z)
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.