Recurrent Diffusion for Large-Scale Parameter Generation

• URL: http://arxiv.org/abs/2501.11587v2
• Date: Tue, 11 Feb 2025 03:29:30 GMT
• Title: Recurrent Diffusion for Large-Scale Parameter Generation
• Authors: Kai Wang, Dongwen Tang, Wangbo Zhao, Konstantin Schürholt, Zhangyang Wang, Yang You,
• Abstract summary: We introduce Recurrent Diffusion for Large Scale Generation (RPG), a novel framework that generates full neural network parameters up to hundreds of millions on a single GPU. RPG serves as a critical advance in AI generating AI, potentially enabling efficient weight generation at scales previously deemed infeasible.
• Score: 52.98888368644455
• License:
• Abstract: Parameter generation has long struggled to match the scale of today large vision and language models, curbing its broader utility. In this paper, we introduce Recurrent Diffusion for Large Scale Parameter Generation (RPG), a novel framework that generates full neural network parameters up to hundreds of millions on a single GPU. Our approach first partitions a networks parameters into non-overlapping tokens, each corresponding to a distinct portion of the model. A recurrent mechanism then learns the inter token relationships, producing prototypes which serve as conditions for a diffusion process that ultimately synthesizes the full parameters. Across a spectrum of architectures and tasks including ResNets, ConvNeXts and ViTs on ImageNet 1K and COCO, and even LoRA based LLMs RPG achieves performance on par with fully trained networks while avoiding excessive memory overhead. Notably, it generalizes beyond its training set to generate valid parameters for previously unseen tasks, highlighting its flexibility in dynamic and open ended scenarios. By overcoming the longstanding memory and scalability barriers, RPG serves as a critical advance in AI generating AI, potentially enabling efficient weight generation at scales previously deemed infeasible.

Related papers

• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive. Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones. We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters [31.55846326336193]
  Graph HyperNetworks (GHNs) have recently shown strong performance in initializing large vision models. LoGAH allows us to predict the parameters of 774-million large neural networks in a memory-efficient manner.
  arXiv  Detail & Related papers  (2024-05-25T15:56:15Z)
• Transfer-Once-For-All: AI Model Optimization for Edge [0.0]
  We propose Transfer-Once-For-All (TOFA) for supernet-style training on small data sets with constant computational training cost. To overcome the challenges arising from small data, TOFA utilizes a unified semi-supervised training loss to simultaneously train all existings within the supernet.
  arXiv  Detail & Related papers  (2023-03-27T04:14:30Z)
• DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion [89.92242000948026]
  We propose a transformer architecture based on a dedicated encoder/decoder framework. Through a dynamic expansion of special tokens, we specialize each forward of our decoder network on a task distribution. Our strategy scales to a large number of tasks while having negligible memory and time overheads.
  arXiv  Detail & Related papers  (2021-11-22T16:29:06Z)
• Recurrent Parameter Generators [42.159272098922685]
  We present a generic method for recurrently using the same parameters for many different convolution layers to build a deep network. We demonstrate how to build a one-layer neural network to achieve similar performance compared to other traditional CNN models.
  arXiv  Detail & Related papers  (2021-07-15T04:23:59Z)
• Highly Efficient Salient Object Detection with 100K Parameters [137.74898755102387]
  We propose a flexible convolutional module, namely generalized OctConv (gOctConv), to efficiently utilize both in-stage and cross-stages multi-scale features. We build an extremely light-weighted model, namely CSNet, which achieves comparable performance with about 0.2% (100k) of large models on popular object detection benchmarks.
  arXiv  Detail & Related papers  (2020-03-12T07:00:46Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.