US 12,340,308 B2
Edge-side federated learning for anomaly detection
Dongjin Song, Princeton, NJ (US); Yuncong Chen, Plainsboro, NJ (US); Cristian Lumezanu, Princeton Junction, NJ (US); Takehiko Mizoguchi, Princeton, NJ (US); Haifeng Chen, West Windsor, NJ (US); and Wei Zhu, Rochester, NY (US)
Assigned to NEC Corporation, Tokyo (JP)
Filed by NEC Laboratories America, Inc., Princeton, NJ (US)
Filed on Mar. 15, 2022, as Appl. No. 17/695,325.
Application 17/695,325 is a continuation of application No. 17/395,118, filed on Aug. 5, 2021.
Claims priority of provisional application 63/291,560, filed on Dec. 20, 2021.
Claims priority of provisional application 63/075,450, filed on Sep. 8, 2020.
Claims priority of provisional application 63/070,437, filed on Aug. 26, 2020.
Claims priority of provisional application 63/062,031, filed on Aug. 6, 2020.
Prior Publication US 2022/0215256 A1, Jul. 7, 2022
Int. Cl. G06N 3/08 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for training a neural network, comprising:
training an edge model exemplar at an edge device, using an initialized global model exemplar, based on information collected at the edge device, including optimizing an objective function:

OG Complex Work Unit Math
where n is a number of multivariate time series segments Xi, θ is a set of parameters for the neural network to be learned, C is a set of edge model exemplars, KL(·) is a Kullback-Leibler divergence, pi is a target cluster membership vector for an ith locally gathered information, qi is a cluster membership vector for the ith locally gathered information, α is a prior distribution over the edge model exemplars, and M(Xi) is a term that preserves local similarity of an original feature space;
transmitting the edge model exemplar to a server without transmitting the information collected at the edge device;
receiving an updated global model exemplar that is based on the edge model exemplar and at least one other model exemplar from another edge device; and
retraining the edge model exemplar using the updated global model exemplar.