Related papers: MetaBalance: Improving Multi-Task Recommendations …
By jointly learning multiple tasks, multi-task learning (MTL) can leverage the shared knowledge across tasks, resulting in improved data efficiency and generalization performance. However, a major challenge in MTL lies in the presence of…
Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing methods use an adaptive weight updating scheme, where task…
Multi-task reinforcement learning (MTRL) aims to train a single agent to efficiently optimize performance across multiple tasks simultaneously. However, jointly optimizing all tasks often yields imbalanced learning: agents quickly solve…
Multi-task learning enables the acquisition of task-generic knowledge by training multiple tasks within a unified architecture. However, training all tasks together in a single architecture can lead to performance degradation, known as…
One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations. However, it is not always trivial to know if an auxiliary task will be helpful for the main…
Multi-task learning (MTL) has received considerable attention, and numerous deep learning applications benefit from MTL with multiple objectives. However, constructing multiple related tasks is difficult, and sometimes only a single task is…
Multi-task post-training of large language models (LLMs) is typically performed by mixing datasets from different tasks and optimizing them jointly. This approach implicitly assumes that all tasks contribute gradients of similar magnitudes;…
Multi-task learning (MTL) is a subfield of machine learning with important applications, but the multi-objective nature of optimization in MTL leads to difficulties in balancing training between tasks. The best MTL optimization methods…
RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across diverse tasks. A straightforward multi-task adaptation of…
Multi-task learning (MTL) has been widely applied in online advertising and recommender systems. To address the negative transfer issue, recent studies have proposed optimization methods that thoroughly focus on the gradient alignment of…
Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting…
One of the grand enduring goals of AI is to create generalist agents that can learn multiple different tasks from diverse data via multitask learning (MTL). However, in practice, applying gradient descent (GD) on the average loss across all…
In multi-task learning, difficulty levels of different tasks are varying. There are many works to handle this situation and we classify them into five categories, including the direct sum approach, the weighted sum approach, the maximum…
The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks. A standard multi-task learning objective is to minimize the average loss across all…
Multitask learning is a widely used paradigm for training models on diverse tasks, with applications ranging from graph neural networks to language model fine-tuning. Since tasks may interfere with each other, a key notion for modeling…
Visual instruction tuning is a key training stage of large multimodal models. However, when learning multiple visual tasks simultaneously, this approach often results in suboptimal and imbalanced overall performance due to latent knowledge…
Meta-learning has proven to be a powerful paradigm for transferring the knowledge from previous tasks to facilitate the learning of a novel task. Current dominant algorithms train a well-generalized model initialization which is adapted to…
The goal of multi-task learning is to learn diverse tasks within a single unified network. As each task has its own unique objective function, conflicts emerge during training, resulting in negative transfer among them. Earlier research…
In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted…
Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of…