arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.17356cs.LGcs.NE
收藏

基于梯度的抽象任务表示推断用于神经网络的泛化

Gradient-based inference of abstract task representations for generalization in neural networks

Massachusetts Institute of Technology(麻省理工学院);Pontificia Universidad Catolica de Chile(智利天主教大学);University of Warwick(华威大学)

Ali Hummos, Felipe del Río, Brabeeba Mien Wang, Julio Hurtado, Cristian B. Calderon, Guangyu Robert Yang

AI总结:

提出基于梯度的推断(GBI)方法,通过优化任务表示层实现任务推断与重组,提升神经网络的学习效率、泛化能力并限制遗忘,同时具备不确定性估计和分布外检测优势。

摘要:

人类和许多动物表现出极具适应性的行为,能够根据内部目标对相同输入做出不同响应。大脑不仅表示执行计算所需的中间抽象,还主动维护计算本身的表示(任务抽象)。计算与其抽象的这种分离与更快的学习、灵活的决策和广泛的泛化能力相关。我们研究这些益处是否能扩展到使用任务抽象训练的神经网络。为了涌现这些益处,需要一种任务推断机制具备两个关键能力:首先,在不再显式提供时推断抽象任务表示的能力(任务推断);其次,操纵任务表示以适应新问题的能力(任务重组)。为此,我们从变分推断的视角将任务推断转化为一个优化问题,并将我们的方法基于期望最大化框架。我们表明,通过神经网络反向传播到任务表示层的梯度是推断当前任务需求的有效启发式方法,我们将此过程称为基于梯度的推断(GBI)。对任务表示层的进一步迭代优化允许重组抽象以适应新情况。使用一个玩具示例、一个新颖的图像分类器和一个语言模型,我们证明GBI提供了更高的学习效率、对新任务的泛化能力并限制了遗忘。此外,我们表明GBI具有独特的优势,例如为不确定性估计保留信息以及检测分布外样本。

英文摘要:

Humans and many animals show remarkably adaptive behavior and can respond differently to the same input depending on their internal goals. The brain not only represents the intermediate abstractions needed to perform a computation but also actively maintains a representation of the computation itself (task abstraction). Such separation of the computation and its abstraction is associated with faster learning, flexible decision-making, and broad generalization capacity. We investigate if such benefits might extend to neural networks trained with task abstractions. For such benefits to emerge, one needs a task inference mechanism that possesses two crucial abilities: First, the ability to infer abstract task representations when no longer explicitly provided (task inference), and second, manipulate task representations to adapt to novel problems (task recomposition). To tackle this, we cast task inference as an optimization problem from a variational inference perspective and ground our approach in an expectation-maximization framework. We show that gradients backpropagated through a neural network to a task representation layer are an efficient heuristic to infer current task demands, a process we refer to as gradient-based inference (GBI). Further iterative optimization of the task representation layer allows for recomposing abstractions to adapt to novel situations. Using a toy example, a novel image classifier, and a language model, we demonstrate that GBI provides higher learning efficiency and generalization to novel tasks and limits forgetting. Moreover, we show that GBI has unique advantages such as preserving information for uncertainty estimation and detecting out-of-distribution samples.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑