论文标题
通过分类器（ - FRE）扩散指导进行元学习
Meta-Learning via Classifier(-free) Diffusion Guidance
论文作者
论文摘要
我们介绍了对神经网络模型进行零拍的权重适应的元学习算法，以表明任务。我们的方法重新利用了自然语言指导和扩散模型的流行生成图像合成技术，以生成适合任务的神经网络权重。我们首先训练无条件的生成超网络模型，以产生神经网络重量。然后，我们训练第二个“指导”模型，鉴于自然语言任务描述，该模型遍历了超网状潜在空间，以零拍的方式找到高性能的任务适应权重。我们探索了潜在空间指导的两种替代方法：“基于HyperClip”的分类器指导和有条件的HyperNetwork潜在扩散模型（“ HyperLDM”），我们表明，这可以从图像生成中常见的无分类器指导技术中受益。最后，我们证明了我们的方法在我们的元VQA数据集中进行了一系列零击学习实验中的现有多任务和元学习方法。
We introduce meta-learning algorithms that perform zero-shot weight-space adaptation of neural network models to unseen tasks. Our methods repurpose the popular generative image synthesis techniques of natural language guidance and diffusion models to generate neural network weights adapted for tasks. We first train an unconditional generative hypernetwork model to produce neural network weights; then we train a second "guidance" model that, given a natural language task description, traverses the hypernetwork latent space to find high-performance task-adapted weights in a zero-shot manner. We explore two alternative approaches for latent space guidance: "HyperCLIP"-based classifier guidance and a conditional Hypernetwork Latent Diffusion Model ("HyperLDM"), which we show to benefit from the classifier-free guidance technique common in image generation. Finally, we demonstrate that our approaches outperform existing multi-task and meta-learning methods in a series of zero-shot learning experiments on our Meta-VQA dataset.
