WeightCLIP：为权重空间学习对齐数据集和模型
WeightCLIP: Aligning Datasets and Models for Weight Space Learning
AI总结：
提出WeightCLIP方法，通过自动编码器和数据集编码器对神经网络及数据集样本编码，用对比目标对齐二者表征，学习数据集对齐的潜在空间，用于不同下游任务，还引入潜在细化过程。
摘要：
权重空间学习旨在学习神经网络权重表征以实现不同下游任务。现有方法缺乏利用模型训练数据集信息塑造权重空间表征的方式。我们提出WeightCLIP，在训练中引入数据集信息来学习神经网络的数据集对齐潜在空间。通过自动编码器对神经网络编码，数据集编码器对数据集样本编码，用对比目标对齐二者，可用于不同下游任务，还引入潜在细化过程。结果表明明确纳入数据集信息可提升权重空间表征在检索、生成和细化方面的表现。代码将在指定网址提供。
英文摘要：
Weight space learning aims to learn representations of neural network (NN) weights, enabling different downstream tasks. Existing approaches show promising performance, but lacking a way to shape these weight-space representations using information about the datasets the models were trained on, thus limiting downstream applications. We propose WeightCLIP, a method for learning a dataset-aligned latent space for neural networks, where datasets information is induced during training. The NNs are encoded as latent representations using an autoencoder, while dataset samples are encoded using a dataset encoder. The two representations are aligned using a contrastive objective, effectively reshaping the weight-space representations according to the datasets. We demonstrate that such representations can be used for different downstream tasks, including mapping dataset information to a weight-space representation that decode to strong models. In addition, we introduce a latent refinement process for generating models that outperforms standard fine-tuning. Overall, our results demonstrate that explicitly incorporating dataset information improves what can be achieved with weight-space representations across retrieval, generation, and refinement. Code will be available at https://github.com/HSG-AIML/WeightCLIP.
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。
