Related papers: Provable Pathways: Learning Multiple Tasks over Mu…

Image galleries provide a rich source of diverse information about a product which can be leveraged across many recommendation and retrieval applications. We study the problem of building a universal image gallery encoder through multi-task…

In this paper, we propose a novel multi-task learning (MTL) framework, called Self-Paced Multi-Task Learning (SPMTL). Different from previous works treating all tasks and instances equally when training, SPMTL attempts to jointly learn the…

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Representation learning of networks has witnessed significant progress in recent times. Such representations have been effectively used for classic network-based machine learning tasks like node classification, link prediction, and network…

Multi-Task Learning (MTL) aims to enhance the model generalization by sharing representations between related tasks for better performance. Typical MTL methods are jointly trained with the complete multitude of ground-truths for all tasks…

Semantic parsers map natural language utterances to meaning representations. The lack of a single standard for meaning representations led to the creation of a plethora of semantic parsing datasets. To unify different datasets and train a…

Neural-based multi-task learning (MTL) has gained significant improvement, and it has been successfully applied to recommendation system (RS). Recent deep MTL methods for RS (e.g. MMoE, PLE) focus on designing soft gating-based…

Effective modeling of heterogeneous subpopulations presents a significant challenge due to variations in individual characteristics and behaviors. This paper proposes a novel approach to address this issue through multi-task learning (MTL)…

Learning multiple domains/tasks with a single model is important for improving data efficiency and lowering inference cost for numerous vision tasks, especially on resource-constrained mobile devices. However, hand-crafting a…

Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they…

Despite the promise of Multi-Task Learning in leveraging complementary knowledge across tasks, existing multi-task optimization (MTO) techniques remain fixated on resolving conflicts via optimizer-centric loss scaling and gradient…

Deep neural networks trained for predicting cellular events from DNA sequence have become emerging tools to help elucidate the biological mechanism underlying the associations identified in genome-wide association studies. To enhance the…

Multi-task learning is a very challenging problem in reinforcement learning. While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains…

The multi-task learning (MTL) paradigm can be traced back to an early paper of Caruana (1997) in which it was argued that data from multiple tasks can be used with the aim to obtain a better performance over learning each task…

Multi-task learning (MTL) is a methodology that aims to improve the general performance of estimation and prediction by sharing common information among related tasks. In the MTL, there are several assumptions for the relationships and…

Modern navigation services often provide multiple paths connecting the same source and destination for users to select. Hence, ranking such paths becomes increasingly important, which directly affects the service quality. We present…

This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates…

Deep learning optimization exhibits structure that is not captured by worst-case gradient bounds. Empirically, gradients along training trajectories are often temporally predictable and evolve within a low-dimensional subspace. In this work…

Unified graph representation learning aims to generate node embeddings, which can be applied to multiple downstream applications of graph analytics. However, existing studies based on graph neural networks and language models either suffer…

An overarching goal in machine learning is to build a generalizable model with few samples. To this end, overparameterization has been the subject of immense interest to explain the generalization ability of deep nets even when the size of…