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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.
Applicant's submission filed on 06/11/2026 has been entered.
Response to Arguments
Applicant’s arguments in view of the claim amendments have been fully considered but are moot in light of a new rejection.
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.
Claim(s) 1-3, 8-13, and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Meng, Chuizheng, Sirisha Rambhatla, and Yan Liu. "Cross-node federated graph neural network for spatio-temporal data modeling." in view of Hu et al. US 2025/0209383 further in view of Cheng, Yong, et al. "Federated learning for privacy-preserving AI."
Regarding claims 1, 11, and 20, Meng teaches “a computer-implemented method, the method comprising: obtaining temporal data from a plurality of distributed client devices in conjunction with a federated machine learning process” (right col. ¶1 “Modeling the dynamics of spatio-temporal data generated from networks of edge devices or nodes (e.g. sensors, wearable devices and the Internet of Things (IoT) devices) is critical for various applications including traffic flow prediction [18, 32], forecasting [4, 24], and user activity detection [20, 29]”), “wherein at least a portion of the data comprises encoded private data and at least a portion of the data is public data” (pg. 2 right col. “Privacy-Preserving Graph Learning. [27] and [22] use statistics of graph structures instead of node information exchange and aggregation to avoid the leakage of node information. Recent works have also incorporated graph learning models with privacy-preserving techniques such as Differential Privacy (DP), Secure Multi-Party Computation (MPC) and Homomorphic Encryption (HE)” federated learning inherently includes private and public data);
“generating a spatio-temporal graph comprising nodes representing the plurality of distributed client devices” (abstract “To bridge this gap, we propose a federated spatio-temporal model – Cross-Node Federated Graph Neural Network (CNFGNN) – which explicitly encodes the underlying graph structure using graph neural network (GNN)-based architecture under the constraint of cross-node federated learning, which requires that data in a network of nodes is generated locally on each node and remains decentralized.”),
While Meng teaches the general graph structure, Hu more specifically teaches “wherein the generating comprises identifying at least one pair of similar nodes based at least in part on the public data and adding an edge to the spatio-temporal graph between the pair of similar nodes” (Hu [0004] “he system may generate a global knowledge graph (and one or more federated knowledge graphs) that includes a number of graph nodes and a number of edges connecting these graph nodes. Each graph node in the knowledge graph may represent a federated node (i.e., local site) or a central server. Each graph node may be associated with a node profile describing the represented federated node (e.g., including information related to associated ML (machine learning) models, policies, parameters, parameter groups, etc.). Each edge connecting two graph nodes may represent a relationship (e.g., connections and interactions) between the two represented federated nodes.” i.e. similar nodes, wherein adding the edge is inherent to the graph construction which determines which nodes are similar)
It would have been obvious to one having ordinary skill in the art at the time that the invention was filed to combine the teachings of Meng with that of Hu since a combination of known methods would yield predictable results. It is very common in graph structures that similar nodes are placed together and connected with edges, as described in Hu. Therefore, these techniques would operate predictably with any other graph structure such as the ones of Meng.
Meng further teaches “aligning encoders of at least two of the distributed client devices […] based at least in part on the spatio-temporal graph comprising the edge between the at least two distributed client devices” (pg. 4 last ¶ “2. To more effectively extract temporal features from each node, we also train the encoder-decoder models on nodes with the FedAvg algorithm proposed in [21]. This enables all nodes to share the same feature extractor and thus share a joint hidden space of temporal features, which avoids the potential overfitting of models on nodes and demonstrates faster convergence and better prediction performance empiric”);
Hu “wherein the method is carried out by at least one computing device” (Hu [0006] “Embodiments according to the invention are in particular disclosed in the attached claims directed to a method, a storage medium, a system and a computer program product, wherein any feature mentioned in one claim category, e.g. method, can be claimed in another claim category, e.g. system, as well.”)
The references do not explicitly teach alignment by increasing similarity of encoders. Cheng however teaches “aligning encoders of at least two of the distributed client devices by updating an encoder of a first one of the distributed client devices to increase a similarity with an encoder of a second one of the distributed client devices […]” (Cheng pg. 3
PNG
media_image1.png
850
1294
media_image1.png
Greyscale
“Step 1: C creates encryption key pairs, and sends the public key to A and B. ˲Step 2: A and B encrypt and exchange intermediate computation results for gradient and loss calculations. ˲Step 3: A and B compute encrypted gradients and add an additional mask, respectively. B also computes the encrypted loss. A and B send encrypted results to C. ˲Step 4: C decrypts gradients and loss and sends the corresponding results back to A and B. A and B unmask the gradients, and update their model parameters accordingly” wherein sharing the encryptions is analogous to aligning encoders as they both protect the private data, see figure 2 encrypted entity alignment)
It would have been obvious to one having ordinary skill in the art at the time that the invention was effectively filed to combine the teachings of Meng and Hu with that of Cheng since “FedRiskCtrl is implemented with the FATE (Federated AI Technology Enabler) platform.d With VFL, the agency A and the bank B do not need to expose their private data to each other, and the model built with FL is expected to perform as well” pg. 3 last ¶. This shows that by combining the techniques the data can be protected.
Note that independent claims 11 and 20 recite the same substantial subject matter as independent claim 1, only differing in embodiment. The differences in embodiment, a system and computer program product compared to a method are taught by Hu [0006] which discloses various embodiments.
Regarding claims 2 and 12, the Meng, Hu, and Cheng references have been addressed above. Meng further teaches “wherein the encoders of the at least two of the distributed client devices produce embeddings of the private data in different vector spaces” (pg. 1 second to last ¶ “CNFGNN decomposes the modeling of temporal and spatial dependencies using an encoder-decoder model on each device” each node/device has its own encoder-decoder)
Regarding claims 3 and 13, the Meng, Hu, and Cheng references have been addressed above. Meng further teaches “wherein a given one of the plurality of distributed client devices comprises a machine learning model that generates a prediction based at least in part on embeddings output by an encoder of the given client device” (pg. 2 §3.1 “One typical task that requires the cross-node federated learning constraint is the prediction of spatio-temporal data generated by a network of sensors”)
Regarding claims 8 and 18, the Meng, Hu, and Cheng references have been addressed above. Meng further teaches “wherein the aligning comprises: processing the spatio-temporal graph using a graph neural network” (abstract “To bridge this gap, we propose a federated spatio-temporal model – Cross-Node Federated Graph Neural Network (CNFGNN) – which explicitly encodes the underlying graph structure using graph neural network (GNN)-based architecture under the constraint of cross-node federated learning”)
Regarding claims 9 and 19, the Meng, Hu, and Cheng references have been addressed above. Meng further teaches “wherein the method is carried out by a central server in a message passing architecture” (federated learning is a decentralized environment i.e. message passing architecture)
Regarding claim 10, the Meng, Hu, and Cheng references have been addressed above. Hu further teaches “wherein software is provided as a service in a cloud environment for performing at least a portion of the federated learning process” (Hu [0084] “Where appropriate, computer system 800 may include one or more computer systems 800; be unitary or distributed; span multiple locations; span multiple machines; span multiple data centers; or reside in a cloud, which may include one or more cloud components in one or more networks”)
Claim(s) 4 and 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Meng in view of Hu and Cheng further in view of Qi et al. US 2024/0330705.
Regarding claims 4 and 14, the Meng, Hu, and Cheng references have been addressed above. The references do not explicitly teach the claim limitations. Qi however teaches “wherein the aligning comprises: applying a negative sampling process based at least in part on pairs of similar nodes that are identified in the spatio-temporal graph” (Qi [0032] “It can be desirable that the negative sampling is implemented while providing for the privacy-preserving benefits that may be achieved through Federated Learning. For instance, data is desirably not exposed to the server.”)
It would have been obvious to one having ordinary skill in the art to combine the teachings of Meng, Hu, and Cheng with that Qi since negative sampling is a known method to preserve privacy.
Claim(s) 6 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Meng in view of Hu and Cheng further in view of Liu, Junxu, et al. "Projected federated averaging with heterogeneous differential privacy."
Regarding claims 6 and 16, the Meng, Hu, and Cheng references have been addressed above. They do not explicitly teach the claim limitations. Liu however teaches wherein the aligning comprises: applying a projection function to the encoded private data of a given one of the distributed client device” (Liu abstract “We propose Projected Federated Averaging (PFA), which extracts the top singular subspace of the model updates submitted by “public” clients and utilizes them to project the model updates of “private” clients before aggregating them”); and
“adding the output of the projection function as a feature to the node corresponding to the given distributed client device” (previous citation)
It would have been obvious to one having ordinary skill in the art at the time that the invention was filed to combine the teachings of Meng, Hu, and Cheng with that of Liu since a combination of known methods would yield predictable results. As shown in Liu, it is known in the art to use projection to keep data safe and therefore would operate in a known and predictable manner with the systems above.
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Meng and Hu and Cheng further in view of Fan, Chenyou, and Ping Liu. "Federated generative adversarial learning."
Regarding claims 7 and 17, the Meng, Hu, and Cheng references have been addressed above. The references do not explicitly teach the limitations. Fan however teaches “wherein the aligning comprises: providing the encoded private data of a first one of the distributed client devices and the public data of a second one of the distributed client devices as input to a discriminator model to determine one or more alignment gradients” (Fan fig. 1
PNG
media_image2.png
464
742
media_image2.png
Greyscale
shows the data going into the discriminator models); and
“sending the alignment gradients to at least one of the first and the second distributed client devices” (previous citation, the arrows are 2-way i.e. data is sent and received “The task of generative learning under federated learning scheme. To preserve data privacy, remote devices exchange only model weights with a central server periodically to learn a global model. No data exchange would happen during any stage of communications.”)
It would have been obvious to one having ordinary skill in the art at the time that the invention was filed to combine the teachings of Meng, Hu, and Cheng with that of Fan since as shown in Fan, the techniques provided privacy preservation which is key in federated learning.
Allowable Subject Matter
No art has been cited for claims 5 and 15.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEVIN W FIGUEROA whose telephone number is (571)272-4623. The examiner can normally be reached Monday-Friday, 10AM-6PM EST.
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, MIRANDA HUANG can be reached at (571)270-7092. 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.
KEVIN W FIGUEROA
Primary Examiner
Art Unit 2124
/Kevin W Figueroa/Primary Examiner, Art Unit 2124
Prosecution Insights