An Overview on Generative AI at Scale with Edge-Cloud Computing
arXiv:2306.17170 · doi:10.36227/techrxiv.23272271
Abstract
As a specific category of artificial intelligence (AI), generative artificial intelligence (GenAI) generates new content that resembles what is created by humans. The rapid development of GenAI systems has created a huge amount of new data on the Internet, posing new challenges to current computing and communication frameworks. Currently, GenAI services rely on the traditional cloud computing framework due to the need for large computation resources. However, such services will encounter high latency because of data transmission and a high volume of requests. On the other hand, edge-cloud computing can provide adequate computation power and low latency at the same time through the collaboration between edges and the cloud. Thus, it is attractive to build GenAI systems at scale by leveraging the edge-cloud computing paradigm. In this overview paper, we review recent developments in GenAI and edge-cloud computing, respectively. Then, we use two exemplary GenAI applications to discuss technical challenges in scaling up their solutions using edge-cloud collaborative systems. Finally, we list design considerations for training and deploying GenAI systems at scale and point out future research directions.
References in corpus (51)
- Auto-Encoding Variational Bayes
- Sequence to Sequence Learning with Neural Networks
- Learning Transferable Visual Models From Natural Language Supervision
- Generative Adversarial Networks: An Overview
- LLaMA: Open and Efficient Foundation Language Models
- Knowledge Distillation: A Survey
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- PaLM: Scaling Language Modeling with Pathways
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- Scaling Laws for Neural Language Models
- Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks
- High-Resolution Image Synthesis with Latent Diffusion Models
- LaMDA: Language Models for Dialog Applications
- Autoencoding beyond pixels using a learned similarity metric
- FastSpeech: Fast, Robust and Controllable Text to Speech
- FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
- A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT
- Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model
- Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- ChatGPT is not all you need. A State of the Art Review of large Generative AI models
- GANSynth: Adversarial Neural Audio Synthesis
- Video Transformers: A Survey
- Point-E: A System for Generating 3D Point Clouds from Complex Prompts
- Carbon Emissions and Large Neural Network Training
- A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?
- A survey of multimodal deep generative models
- AI-Generated Content (AIGC): A Survey
- Text-to-image Diffusion Models in Generative AI: A Survey
- ScanGAN360: A Generative Model of Realistic Scanpaths for 360 Images
- Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services
- Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networks
- A Survey of Vision-Language Pre-Trained Models
- A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI
- AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing
- NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
- A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models
- DefakeHop: A Light-Weight High-Performance Deepfake Detector
- Towards Performance Clarity of Edge Video Analytics
- NITES: A Non-Parametric Interpretable Texture Synthesis Method
- A Focused Study on Sequence Length for Dialogue Summarization
- Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services
- Green Learning: Introduction, Examples and Outlook
- HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud Computing
- TGHop: An Explainable, Efficient and Lightweight Method for Texture Generation
- A survey on Variational Autoencoders from a GreenAI perspective
- A Perceptual Quality Assessment Exploration for AIGC Images
- GENHOP: An Image Generation Method Based on Successive Subspace Learning
- PAGER: Progressive Attribute-Guided Extendable Robust Image Generation