A Blockchain-based Platform for Reliable Inference and Training of Large-Scale Models

• URL: http://arxiv.org/abs/2305.04062v1
• Date: Sat, 6 May 2023 14:21:41 GMT
• Title: A Blockchain-based Platform for Reliable Inference and Training of Large-Scale Models
• Authors: Sanghyeon Park, Junmo Lee, Soo-Mook Moon
• Abstract summary: We introduce BRAIN, a novel platform specifically designed to ensure reliable inference and training of large models. BRAIN harnesses a unique two-phase transaction mechanism, allowing real-time processing via pipelining. BRAIN delivers considerably higher inference throughput at reasonable gas fees.
• Score: 1.323497585762675
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: As artificial intelligence (AI) continues to permeate various domains, concerns surrounding trust and transparency in AI-driven inference and training processes have emerged, particularly with respect to potential biases and traceability challenges. Decentralized solutions such as blockchain have been proposed to tackle these issues, but they often struggle when dealing with large-scale models, leading to time-consuming inference and inefficient training verification. To overcome these limitations, we introduce BRAIN, a Blockchain-based Reliable AI Network, a novel platform specifically designed to ensure reliable inference and training of large models. BRAIN harnesses a unique two-phase transaction mechanism, allowing real-time processing via pipelining by separating request and response transactions. Each randomly-selected inference committee commits and reveals the inference results, and upon reaching an agreement through a smart contract, then the requested operation is executed using the consensus result. Additionally, BRAIN carries out training by employing a randomly-selected training committee. They submit commit and reveal transactions along with their respective scores, enabling local model aggregation based on the median value of the scores. Experimental results demonstrate that BRAIN delivers considerably higher inference throughput at reasonable gas fees. In particular, BRAIN's tasks-per-second performance is 454.4293 times greater than that of a naive single-phase implementation.

Related papers

• Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning [15.605693371392212]
  Multi-Agent Deep Reinforcement Learning (MDRL) is a promising research area in which agents learn complex behaviors in cooperative or competitive environments. Recent works proposing Federated Reinforcement Learning (FRL) to tackle these issues suffer from problems related to model restrictions and maliciousness. We propose a novel-assisted Multi-Expert Demonstration Cloning (MEDC) framework for MDRL.
  arXiv  Detail & Related papers  (2025-01-19T04:20:24Z)
• Outcome-Refining Process Supervision for Code Generation [28.6680126802249]
  Large Language Models struggle with complex programming tasks that require deep algorithmic reasoning. We propose Outcome-Refining Process Supervision, a novel paradigm that treats outcome refinement itself as the process to be supervised. Our approach achieves significant improvements across 5 models and 3 datasets: an average of 26.9% increase in correctness and 42.2% in efficiency.
  arXiv  Detail & Related papers  (2024-12-19T17:59:42Z)
• Bidirectional Decoding: Improving Action Chunking via Closed-Loop Resampling [51.38330727868982]
  Bidirectional Decoding (BID) is a test-time inference algorithm that bridges action chunking with closed-loop operations. We show that BID boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks [52.46420522934253]
  We introduce LoRA-Ensemble, a parameter-efficient deep ensemble method for self-attention networks. By employing a single pre-trained self-attention network with weights shared across all members, we train member-specific low-rank matrices for the attention projections. Our method exhibits superior calibration compared to explicit ensembles and achieves similar or better accuracy across various prediction tasks and datasets.
  arXiv  Detail & Related papers  (2024-05-23T11:10:32Z)
• Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training [34.80971707794908]
  Federated Split Decision Transformer (FSDT) is an innovative framework designed explicitly for AI agent decision tasks. FSDT framework excels at navigating the intricacies of personalized agents by harnessing distributed data for training. Our findings underscore the efficacy of the FSDT framework in effectively leveraging distributed offline reinforcement learning data to enable powerful multi-type agent decision systems.
  arXiv  Detail & Related papers  (2024-05-22T08:37:37Z)
• Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning [20.412469498888292]
  Federated Learning (FL) enables multiple devices to collaboratively train a shared model. The selection of participating devices in each training round critically affects both the model performance and training efficiency. We introduce a novel device selection solution called FedRank, which is an end-to-end, ranking-based approach.
  arXiv  Detail & Related papers  (2024-05-07T08:44:29Z)
• Secure Decentralized Learning with Blockchain [13.795131629462798]
  Federated Learning (FL) is a well-known paradigm of distributed machine learning on mobile and IoT devices. To avoid the single point of failure problem in FL, decentralized learning (DFL) has been proposed to use peer-to-peer communication for model aggregation.
  arXiv  Detail & Related papers  (2023-10-10T23:45:17Z)
• Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction [76.26710990597498]
  We show that the class-imbalance of the grouped data from randomly selected clients can lead to significant performance degradation. Based on our key observation, we design an efficient client sampling mechanism, i.e., Federated Class-balanced Sampling (Fed-CBS) In particular, we propose a measure of class-imbalance and then employ homomorphic encryption to derive this measure in a privacy-preserving way.
  arXiv  Detail & Related papers  (2022-09-30T05:42:56Z)
• Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning [55.198301429316125]
  Machine learning (ML) is a key technique for big-data-driven modelling and analysis of massive Internet of Things (IoT) based intelligent and ubiquitous computing. For fast-increasing applications and data amounts, distributed learning is a promising emerging paradigm since it is often impractical or inefficient to share/aggregate data. This paper studies the problem of training an ML model over decentralized systems, where data are distributed over many user devices.
  arXiv  Detail & Related papers  (2022-02-07T15:04:15Z)
• Secure Distributed Training at Scale [65.7538150168154]
  Training in presence of peers requires specialized distributed training algorithms with Byzantine tolerance. We propose a novel protocol for secure (Byzantine-tolerant) decentralized training that emphasizes communication efficiency.
  arXiv  Detail & Related papers  (2021-06-21T17:00:42Z)
• Low-Latency Federated Learning over Wireless Channels with Differential Privacy [142.5983499872664]
  In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server. In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement.
  arXiv  Detail & Related papers  (2021-06-20T13:51:18Z)

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.