DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . This office action is in response to the Application filed on 10/21/2022. Claims 1-20 are presented for examination.
Priority
Application is a continuation of International Application No. PCT/EP2020/061440, filed on April 24, 2020.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 01/31/2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 5-6, 7-8, 10-13, and 17-20 are rejected under 35 U.S.C. 102(a) as being anticipated by Arivazhagan et al. “Federated Learning with Personalization Layers” 12/02/2019.
Regarding Claim 1 Arivazhagan teaches A client computing device comprising: a data storage unit; a memory configured to store instructions; and a processor coupled to the memory and configured to execute the instructions to cause the client computing device to: store a local dataset in the data storage unit; (Arivazhagan, page 1, section 1, teaches that federated learning involves storing local data on client devices. Arivazhagan, page 2, Figure 1, teaches a personalized federated learning where clients have individual data. (i.e. local dataset)) obtain a model of a neural network from a server computing device, wherein the model comprises a set of common layers and a set of client-specific layers; (Arivazhagan, page 3-4, section 3, teaches the obtaining of base layers (i.e. common layers) from a server and obtaining a set of personalized layers (i.e. client-specific layers)) train the model based on the local dataset to obtain an updated set of common layers and an updated set of client-specific layers, wherein the local dataset is stored at the client computing device send the updated set of common layers to the server computing device; (Arivazhagan, page 3-4, section 3, teaches the training of the model on the client device to get a set of updated personalized layers (i.e. client-specific layers) and base layers (i.e. common layers), wherein the base layers are sent to the server when they are updated.) and store the updated set of client-specific layers. (Arivazhagan, page 3-4, section 3, teaches the storing of the personalized layers in the client device.)
Regarding Claim 5 Arivazhagan teaches the client computing device according to claim 1, wherein the processor is further configured to execute the instructions to cause the client computing device to: receive an aggregated set of common layers from the server computing device; and update the model based on the aggregated set of common layers. (Arivazhagan, page 4, section 3.2, teaches the client devices sending the updated base layers (i.e. common layers) to the server, and the server aggregating the base layers and sending them back to the client when the aggregation process is done. The client then updates its model to incorporate the new base layers.)
Regarding Claim 6 Arivazhagan teaches the client computing device according to claim 5, wherein, for updating the model based on the aggregated set of common layers, the processor is further configured to execute the instructions to cause client computing device to concatenate the aggregated set of common layers and the updated set of client-specific layers. (Arivazhagan, page 4, section 3.2, teaches the combining (i.e. concatenate) the updated base layers (i.e. common layers) with the updated personalized layer to create the client model)
Regarding Claim 7 Arivazhagan teaches the client computing device according to claim 1, wherein the set of client-specific layers comprises last fully connected layers of the neural network, and/or wherein the set of common layers comprises convolutional layers of the neural network. (Arivazhagan, page 5, section 4.2, teaches the personalization layers (i.e. client-specific layers) being fully connected layers of the neural network. Arivazhagan, page 5, section 4.1, teaches the use of convolutional neural networks in the federated learning implementation meaning that the base layers (i.e. common layers) are convolutional layers in the neural network)
Regarding Claim 8 Arivazhagan teaches A server computing device to comprising: a memory configured to store instructions; and a processor coupled to the memory and configured to execute the instructions to cause the server computing device to: send a model of a neural network to each of a plurality of client computing devices, wherein the model comprises a set of common layers and a set of client-specific layers; (Arivazhagan, page 3-4, section 3, teaches the sending of base layers (i.e. a neural network model) to client devices that then combine the base layers with the personalized layers to create a personalized model on the client device. The base layers constitute a model that is trained and the personalized layers are appended to the model to create a new model) and receive, from each of the plurality of client computing devices, an updated set of common layers. (Arivazhagan, page 3-4, section 3, teaches the receiving of updated base layers (i.e. common layers) from the client devices.)
Regarding Claim 10 Arivazhagan teaches the server computing device according to claim 8, wherein the processor is further configured to execute the instructions to cause the server computing device further configured to aggregate the received updated sets of common layers to obtain an aggregated set of common layers; and send the aggregated set of common layers to each of the plurality of client computing devices. (Arivazhagan, page 4, section 3.2, teaches the receiving of the updated base layers (i.e. common layers) from the client devices and aggregates them together then sends them to the client devices.)
Regarding Claim 11 Arivazhagan teaches the server computing device according to claim 10, wherein, for aggregating the received updated sets of common layers to obtain the aggregated set of common layers, processor is further configured to execute the instructions to cause server computing device to perform an average function, a weighted average function, a harmonic average function, or a maximum function on the received updated sets of common layers. (Arivazhagan, page 4, section 3.2, teaches the use of a weighted combination function (i.e. weighted average function) across all the client updated base layers that are received.)
Regarding Claim 12 Arivazhagan teaches the server computing device according to claim 8, wherein the set of client-specific layers comprises last fully connected layers of the neural network and/or wherein the set of common layers comprises convolutional layers of the neural network. (Arivazhagan, page 5, section 4.2, teaches the personalization layers (i.e. client-specific layers) being fully connected layers of the neural network. Arivazhagan, page 5, section 4.1, teaches the use of convolutional neural networks in the federated learning implementation meaning that the base layers (i.e. common layers) are convolutional layers in the neural network)
Regarding Claim 13 Arivazhagan teaches A method implemented by a client computing device, the method comprising: storing a local dataset; (Arivazhagan, page 1, section 1, teaches that federated learning involves storing local data on client devices. Arivazhagan, page 2, Figure 1, teaches a personalized federated learning where clients have individual data. (i.e. local dataset)) obtaining, a model of a neural network from a server computing device, wherein the model comprises a set of common layers and a set of client-specific layers; (Arivazhagan, page 3-4, section 3, teaches the obtaining of base layers (i.e. common layers) from a server and obtaining a set of personalized layers (i.e. client-specific layers)) training, by the client computing device, the model based on the local dataset to obtain an updated set of common layers and an updated set of client-specific layers: sending, to the server computing device, the updated set of common layers (Arivazhagan, page 3-4, section 3, teaches the training of the model on the client device to get a set of updated personalized layers (i.e. client-specific layers) and base layers (i.e. common layers), wherein the base layers are sent to the server when they are updated.) and storing, the updated set of client-specific layers. (Arivazhagan, page 3-4, section 3, teaches the storing of the personalized layers in the client device.)
Regarding Claim 17 Arivazhagan teaches the method according to claim 13, wherein the method further comprises: receiving, an aggregated set of common layers from the server computing device; and updating, the model based on the aggregated set of common layers. (Arivazhagan, page 4, section 3.2, teaches the client devices sending the updated base layers (i.e. common layers) to the server, and the server aggregating the base layers and sending them back to the client when the aggregation process is done. The client then updates its model to incorporate the new base layers.)
Regarding Claim 18 Arivazhagan teaches the method according to claim 17, wherein the method further comprises concatenating, the aggregated set of common layers and the updated set of client-specific layers. (Arivazhagan, page 4, section 3.2, teaches the combining (i.e. concatenate) the updated base layers (i.e. common layers) with the updated personalized layer to create the client model)
Regarding Claim 19 Arivazhagan teaches the method according to claim 13, wherein the set of client-specific layers comprises last fully connected layers of the neural network. (Arivazhagan, page 5, section 4.2, teaches the personalization layers (i.e. client-specific layers) being fully connected layers of the neural network.)
Regarding Claim 20 Arivazhagan teaches the method according to claim 19, wherein the set of common layers comprises convolutional layers of the neural network. (Arivazhagan, page 5, section 4.1, teaches the use of convolutional neural networks in the federated learning implementation meaning that the base layers (i.e. common layers) are convolutional layers in the neural network)
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 2-4, 9, and 14-16 are rejected under 35 U.S.C. 103 as being unpatentable over Arivazhagan et al. “Federated Learning with Personalization Layers” 12/02/2019 in view of Liu et al. “Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems With Heterogeneous Sensor Data” 02/26/2020.
Regarding Claim 2 Arivazhagan teaches the client computing device according to claim 1, wherein the set of common layers 1…, and wherein the set of client-specific layers comprises classification. (Arivazhagan, page 5, section 4.2, teaches the personalization layers (i.e. client-specific layers) being classifier layers (i.e. classification))
Arivazhagan does not teach 1…comprises feature-extraction information… However, Liu in analogous art teaches this limitation (Liu, page 3513 section D and Fig 4, teaches the use of layers sent from the server to each client (i.e. common layers) that comprise feature extraction information)
It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine Liu’s teaching of common feature extraction layers with Arivazhagan’s teaching of A federated learning system. The motivation to do so would be to would be to have a common system of feature extraction between each of the client devices to allow for features to be extracted in a common way between client devices and to allow for better learning over the features.
Regarding Claim 3 the combination of Arivazhagan and Liu teaches The client computing device according to claim 1, wherein, for training the model based on the local dataset to obtain the updated set of common layers and the updated set of client-specific layers, (Arivazhagan, page 3-4, section 3, teaches the training of a neural network model to obtain an updated set of base (i.e. common) and personalized layers (i.e. client-specific layers)) the processor is further configured to execute the instructions to cause the client computing device to: perform feature extraction on the local dataset using the set of common layers to obtain extracted features of the local dataset; ((Liu, page 3513 section D and Fig 4, teaches feature extraction layers that were sent from a server to be used by client devices (i.e. common layers performing feature extraction). The client devices use local data that is unique to the client devices.) and perform classification of the extracted features of the local dataset using the set of client-specific layers. (Arivazhagan, page 3-4, section 3, teaches the personalized layers (i.e. client-specific layers) performing classification on the features that are output from the base layers (i.e. common layers).)
Regarding Claim 4 Arivazhagan and Liu teaches The client computing device according to claim 3, wherein, for performing the classification of the extracted features of the local dataset, (Arivazhagan, page 3-4, section 3, teaches the personalized layers (i.e. client-specific layers) performing classification on the features that are output from the base layers (i.e. common layers).) the processor is further configured to execute the instructions to cause the client computing device to use a normalized exponential function to output labels of the local dataset with probabilities. (Liu, page 3513 section D and Fig 4, teaches the use of softmax layers (i.e. a normalized exponential function) to output the labels and probabilities of the federated learning model)
Regarding Claim 9 Arivazhagan and Liu teaches the server computing device according to claim 8, wherein the set of common layers comprises 2…, and the set of client-specific layers comprises classification information for classification. (Arivazhagan, page 5, section 4.2, teaches the personalization layers (i.e. client-specific layers) being classifier layers (i.e. classification)) Arivazhagan does not teach 2… feature-extraction information for feature extraction… However, Liu in analogous art teaches this limitation (Liu, page 3513 section D and Fig 4, teaches the use of layers sent from the server to each client (i.e. common layers) that comprise feature extraction information)
It would have been obvious to one skilled in the art before the effective filing date of the claimed invention to combine Liu’s teaching of common feature extraction layers with Arivazhagan’s teaching of A federated learning system. The motivation to do so would be to would be to have a common system of feature extraction between each of the client devices to allow for features to be extracted in a common way between client devices and to allow for better learning over the features.
Regarding Claim 14 Arivazhagan and Liu teaches the method according to claim 13, wherein the set of common layers comprises feature extraction information, (Liu, page 3513 section D and Fig 4, teaches the use of layers sent from the server to each client (i.e. common layers) that comprise feature extraction information) and wherein the set of client specific layers comprises classification information for classification. (Arivazhagan, page 5, section 4.2, teaches the personalization layers (i.e. client-specific layers) being classifier layers (i.e. classification))
Regarding Claim 15 Arivazhagan and Liu teaches the method according to claim 13, wherein the method further comprises: performing, feature extraction on the local dataset using the set of common layers to obtain extracted features of the local dataset; ((Liu, page 3513 section D and Fig 4, teaches feature extraction layers that were sent from a server to be used by client devices (i.e. common layers performing feature extraction). The client devices use local data that is unique to the client devices.) and performing, classification of the extracted features of the local dataset using the set of client-specific layers. (Arivazhagan, page 3-4, section 3, teaches the personalized layers (i.e. client-specific layers) performing classification on the features that are output from the base layers (i.e. common layers).)
Regarding Claim 16 Arivazhagan and Liu teaches the method according to claim 15, wherein the method further comprises using, a normalized exponential function to output labels of the local dataset with probabilities. (Liu, page 3513 section D and Fig 4, teaches the use of softmax layers (i.e. a normalized exponential function) to output the labels and probabilities of the federated learning model)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to THOMAS B LANE whose telephone number is (571)272-1872. The examiner can normally be reached M-Th: 7am-5pm; F: Out of Office.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, MARIELA REYES can be reached at (571) 270-1006. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/THOMAS BERNARD LANE/ Examiner, Art Unit 2142 /HAIMEI JIANG/Primary Examiner, Art Unit 2142