Systems and methods for monetizing data in decentralized model building for machine learning using a blockchain
AssigneeHewlett Packard Enterprise Development LP
InventorsSathyanarayanan Manamohan, Vishesh Garg, Krishnaprasad Lingadahalli Shastry
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for leveraging blockchain technology in a swarm learning context, where nodes of a blockchain network that contribute data to training a machine learning model using their own local data can be rewarded. In order to conduct such data monetization in a fair and accurate manner, the systems and methods rely on various phases in which Merkle trees are used and corresponding Merkle roots are registered in a blockchain ledger. Moreover, any claims for a reward are challenged by peer nodes before the reward is distributed.
Claims21
1-20. (canceled)
A data monetization network node operating in a blockchain network, comprising:
- a processor;
- and
- a memory unit operatively connected to the processor and including computer code, wherein the processor executes the computer code to:
- build a hash tree representing a non-duplicative value of an encrypted data record extracted from a machine learning model, and register a corresponding hash tree root in a distributed ledger of the blockchain network;
- submit a claim for a reward represented by a height of the hash tree, wherein the height of the hash tree is measured from a leaf node of the hash tree to a root node of the hash tree;
- provide a hash tree proof to another network node in the blockchain network, the hash tree proof verifying the height of the hash;
- and
- calculate an amount of individual data points contributed by the data monetization network node based upon the height of the hash tree, the calculated amount of individual data points comprising a share of a monetization reward for training of the machine learning model.
A data monetization network node operating in a blockchain network, comprising:
- a processor;
- and
- a memory unit operatively connected to the processor and including computer code, wherein the processor executes the computer code to:
- encrypt a data record extracted from a machine learning model;
- hash the encrypted data record to generate a non-duplicative value of the encrypted data record;
- store the non-duplicative value;
- build a hash tree based on the value, and register a corresponding hash tree root in a distributed ledger of the blockchain network;
- submit a claim for a reward represented by a height of the hash tree, wherein the height of the hash tree is measured from a leaf node of the hash tree to a root node of the hash tree;
- calculate a percentage share of a monetization reward for training of the machine learning model;
- register the calculated percentage share of the monetization reward to the distributed ledger;
- and
- receive the calculated percentage share of the monetization reward.
A node participating in a blockchain network, comprising:
- a processor;
- and
- a memory unit operatively connected to the processor and including computer code, wherein the processor executes the computer code to:
- submit a verification challenge of a reward claim submitted by another network node participating in the blockchain network, the reward claim based on a height of a hash tree, wherein the height of the hash tree is measured from a leaf node of the hash tree to a root node of the hash tree;
- receive a hash tree proof from the other blockchain network node, the hash tree proof to verify the height of the hash tree;
- determine an outcome of the verification challenge based on the hash tree proof;
- and
- record the outcome of the verification challenge in a distributed ledger of the blockchain network.
Dependencies are inferred from the claim text.