Collaborative model execution
An example operation may include one or more of receiving, at a node, a request to execute a software model that has been decomposed into a plurality of sequential sub-components, executing a sub-component from among the plurality of sub-components based on input data included in the received request to generate output data, hashing the input data and the output data to generate a hashed execution result of the sub-component, and storing the hashed execution result of the sub-component within a block among a hash-linked chain of blocks which include hashed execution results of other sub-components of the software model executed by other nodes.
1. A computing node comprising:
a network interface configured to receive a request to execute a software model that has been decomposed into a plurality of sequential sub-components; and
a processor configured to execute a sub-component from among the plurality of sub-components based on input data included in the received request to generate output data, hash the input data and the output data to generate a hashed execution result of the sub-component, and store the hashed execution result of the sub-component within a block among a hash-linked chain of blocks which include hashed execution results of other sub-components of the software model executed by other nodes;
wherein the processor is further configured to aggregate the hashed execution result of the sub-component with the hashed execution results of the other sub-components to generate an aggregated execution result of the software model.
2. The computing node of claim 1 , wherein the request is received from a different computing node which executed a previous sub-component in the sequence.
3. The computing node of claim 1 , wherein the request is received from an orchestrator that coordinates independent execution of the plurality of sub-components in sequence via a plurality of computing nodes.
4. The computing node of claim 1 , wherein one or more other sub-components of the software model are hidden from the computing node.
5. The computing node of claim 1 , wherein the processor is further configured to hash code of the sub-component executed by the computing node to generate the hashed execution result.
6. The computing node of claim 1 , wherein the network interface is further configured to transmit the aggregated execution result of the software model to a client device.
7. The computing node of claim 1 , wherein the network interface is further configured to transmit, to another computing node, the output data and a request to execute a next sub-component among the plurality of sequential sub-components.
8. A method comprising:
receiving, at a node, a request to execute a software model that has been decomposed into a plurality of sequential sub-components;
executing a sub-component from among the plurality of sub-components based on input data included in the received request to generate output data;
hashing the input data and the output data to generate a hashed execution result of the sub-component; and
storing the hashed execution result of the sub-component within a block among a hash-linked chain of blocks which include hashed execution results of other sub-components of the software model executed by other nodes;
wherein the hashed execution result of the sub-component is aggregated with the hashed execution results of the other sub-components to generate an aggregated execution result of the software model.
9. The method of claim 8 , wherein the request is received from a different node which executed a previous sub-component in the sequence.
10. The method of claim 8 , wherein the request is received from an orchestrator that coordinates independent execution of the plurality of sub-components in sequence via a plurality of nodes.
11. The method of claim 8 , wherein one or more other sub-components of the software model are hidden from the node.
12. The method of claim 8 , wherein the hashing further comprises hashing code of the sub-component executed by the node to generate the hashed execution result.
13. The method of claim 8 , further comprising outputting the aggregated execution result of the software model to a client device.
14. The method of claim 8 , further comprising transmitting, to another node, the output data and a request to execute a next sub-component among the plurality of sequential sub-components.
15. A non-transitory computer readable medium comprising instructions, that when read by a processor, cause the processor to perform a method comprising:
receiving, at a node, a request to execute a software model that has been decomposed into a plurality of sequential sub-components;
executing a sub-component from among the plurality of sub-components based on input data included in the received request to generate output data;
hashing the input data and the output data to generate a hashed execution result of the sub-component; and
storing the hashed execution result of the sub-component within a block among a hash-linked chain of blocks which include hashed execution results of other sub-components of the software model executed by other nodes;
wherein the hashed execution result of the sub-component is aggregated with the hashed execution results of the other sub-components to generate an aggregated execution result of the software model.
16. The non-transitory computer readable medium of claim 15 , wherein the request is received from a different node which executed a previous sub-component in the sequence.
17. The non-transitory computer readable medium of claim 15 , wherein the request is received from an orchestrator that coordinates independent execution of the plurality of sub-components in sequence via a plurality of nodes.
18. The non-transitory computer readable medium of claim 15 , wherein the hashing further comprises hashing code of the sub-component executed by the node to generate the hashed execution result.