Learning Task Sampling Policy for Multitask Learning (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to train multi-task models with auxiliary tasks are limited by the number of combinations and the importance of each auxiliary task is not known a priori.
Approach: They propose a search method that automatically assigns importance weights to auxiliary tasks to improve the target task quality.
Outcome: The proposed method outperforms uniform sampling and the corresponding single-task baseline on XNLI and GLUE.

Similar Papers

Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity (2021.emnlp-main)

Copied to clipboard

Challenge: Multi-task auxiliary learning uses a set of relevant auxiliary tasks to improve performance of a primary task.
Approach: They propose a time-efficient sampling method to select the most beneficial sub-datasets from the auxiliary tasks to achieve efficient multi-task auxiliary learning.
Outcome: The proposed method significantly outperforms random sampling and ST-DNN on three benchmark datasets.
Improving Multitask Retrieval by Promoting Task Specialization (2023.tacl-1)

Copied to clipboard

Challenge: despite its practical appeal, naive multitask retrieval lags behind task-specific retrieval.
Approach: They propose to train a multitask retriever that promotes task specialization . the model is highly performant on the KILT benchmark .
Outcome: The proposed model outperforms task-specific retrievals on the KILT benchmark . it learns parameters that are more task-specialized than naive retrieval without prompting or adaptive learning.
Transductive Auxiliary Task Self-Training for Neural Multi-Task Models (D19-61)

Copied to clipboard

Challenge: Multi-task learning and self-training are two common ways to improve a machine learning model’s performance in settings with limited training data.
Approach: They propose a transductive auxiliary task self-training procedure that trains a model on auxiliary tasks and test instances with auxiliary labels generated by a single-task version of the model.
Outcome: The proposed method improves accuracy by 9.56% over the pure multi-task model for dependency relation tagging and 13.03% for semantic taging.
Dynamic Sampling Strategies for Multi-Task Reading Comprehension (2020.acl-main)

Copied to clipboard

Challenge: Prior work focused on model architecture or generalization to held out datasets and largely passed over the particulars of the multi-task learning set up.
Approach: They propose a dynamic sampling strategy that selects instances proportional to the model's current performance on a dataset relative to its single task performance.
Outcome: The proposed model outperforms the best model on ORB, a recent multitask reading comprehension benchmark.
AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning (N19-1)

Copied to clipboard

Challenge: Multi-task learning is an inductive transfer mechanism that leverages information from related tasks to improve the primary model's generalization performance.
Approach: They propose a multitask learning pipeline that finds relevant auxiliary tasks and learns their mixing ratio.
Outcome: The proposed model can find relevant auxiliary tasks and learn their mixing ratio . the proposed model achieves significant performance boosts on several primary tasks .
MetaWeighting: Learning to Weight Tasks in Multi-Task Learning (2022.findings-acl)

Copied to clipboard

Challenge: Existing task weighting methods assign weights only based on training losses, while ignoring the gap between the training loss and generalization loss.
Approach: They propose a task weighting algorithm which automatically weights the tasks via a learning-to-learn paradigm and a multi-task text classification paradigm.
Outcome: Extensive experiments show that the proposed method outperforms existing methods in multi-task text classification.
Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning (2022.naacl-main)

Copied to clipboard

Challenge: Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks.
Approach: They aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning by increasing the number of tasks and incorporating smaller sets of related tasks.
Outcome: The proposed model improves on unseen target tasks by increasing the scale of multi-task learning to incorporate more tasks and developing similarity metrics to incorporate tasks related to the target task.
Multi-task Active Learning for Pre-trained Transformer-based Models (2022.tacl-1)

Copied to clipboard

Challenge: Multi-task learning requires annotating the same text with multiple annotation schemes, which can be costly and laborious.
Approach: They propose to use multi-task active learning paradigm to optimize annotation processes by iteratively selecting unlabeled examples whose annotation is most valuable for the NLP model.
Outcome: The proposed model minimizes annotation efforts for multi-task NLP models by iterating on the most valuable examples.
Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks (2020.acl-main)

Copied to clipboard

Challenge: Multitask learning and transfer learning are techniques to overcome data scarcity . finding suitable auxiliary datasets for multitask learning is a trial-and-error approach .
Approach: They propose to automatically assess the similarity of sequence tagging datasets to identify beneficial auxiliary data for MTL or TL setups.
Outcome: The proposed methods can compute similarity between two sequence tagging datasets . they show that the same measures correlate with the change in test score of the auxiliary dataset .
Improved Policy Optimization for Mixture-of-Experts Models: Importance Sampling and Rewarding from an Expert-Centric Perspective (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to reinforcement learning (RL) suffer from training instability . existing approaches often ignore token-specific discrepancies in expert assignments .
Approach: They propose to introduce expert-level importance sampling to reduce complexity of RL . they propose to leverage expert-centric granularity to ensure a rigorous alignment between reward signals and policy updates.
Outcome: The proposed method outperforms strong baselines across reasoning tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations