# US 2026/0087331 A1 · Model compression for neural networks > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0087331 A1 - Document ID: US20260087331A1 - Status: Published application - Kind: A1 - Application number: 18/895,537 - Filed: 2024-09-25 - Published: 2026-03-26 - Earliest claimed: 2024-09-25 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: SURIYA T SKARIAH; PRASHANSHA GUPTA; RAHUL M RAO - Web page: https://patentgrep.com/patent/US20260087331A1 ## CPC - G06N 3/0495: Quantised networks; Sparse networks; Compressed networks - G06N 3/08: Learning methods - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Model compression for neural networks, including: determining, during training of a neural network model, for each of a plurality of training iterations, a corresponding value for a plurality of weights; calculating, for each weight of the plurality of weights and based on the corresponding value for each of the plurality of weights, an importance metric; calculating a plurality of quantized weights by binning the plurality of weights based on the importance metric; and updating the neural network model based on the plurality of quantized weights. ## Claims ### Claim 1 A method comprising: determining, during training of a neural network model, for each of a plurality of training iterations, a corresponding value for a plurality of weights; calculating, for each weight of the plurality of weights and based on the corresponding value for each of the plurality of weights, an importance metric; calculating a plurality of quantized weights by binning the plurality of weights based on the importance metric; and updating the neural network model based on the plurality of quantized weights. ### Claim 2 (depends on 1) The method of claim 1, wherein the importance metric comprises a coefficient of variation. ### Claim 3 (depends on 1) The method of claim 1, further comprising calculating, for each weight of the plurality of weights, a direction of change. ### Claim 4 (depends on 3) The method of claim 3, wherein calculating, for each weight of the plurality of weights, the direction of change comprises assigning, to a given weight of the plurality of weights, the direction of change based on a number of times that the given weight changed according to the direction of change during training of the neural network model. ### Claim 5 (depends on 3) The method of claim 3, wherein calculating, for each weight of the plurality of weights, the direction of change comprises assigning, to a given weight of the plurality of weights, the direction of change based on a delta between a first value for the given weights and a last value for the given weight during training of the neural network model. ### Claim 6 (depends on 1) The method of claim 1, wherein calculating the plurality of quantized weights comprises: selecting a subset of the plurality of weights based on the importance metric; clustering the subset of the plurality of weights into a plurality of clusters; mapping each weight of the subset of the plurality of weights to a centroid of a corresponding cluster of the plurality of clusters; and mapping each weight of a remainder of the plurality of weights to a nearest centroid based on a corresponding direction of change. ### Claim 7 (depends on 1) The method of claim 1, wherein calculating the plurality of quantized weights comprises: initializing, for the plurality of weights, a plurality of centroids; scaling, based on the importance metric, a distance for each weight of the plurality of weights to the plurality of centroids; updating the plurality of centroids based on a scaled distance for each weight of the plurality of weights; and mapping each weight of the plurality of weights to a nearest centroid of the updated plurality of centroids. ### Claim 8 An apparatus comprising: a memory; and a processing device operatively coupled to the memory, the processing device configured to: determine, during training of a neural network model, for each of a plurality of training iterations, a corresponding value for a plurality of weights; calculate, for each weight of the plurality of weights and based on the corresponding value for each of the plurality of weights, an importance metric; calculate a plurality of quantized weights by binning the plurality of weights based on the importance metric; and update the neural network model based on the plurality of quantized weights. ### Claim 9 (depends on 8) The apparatus of claim 8, wherein the importance metric comprises a coefficient of variation. ### Claim 10 (depends on 8) The apparatus of claim 8, wherein the processing device is further configured to calculate, for each weight of the plurality of weights, a direction of change. ### Claim 11 (depends on 10) The apparatus of claim 10, wherein, to calculate, for each weight of the plurality of weights, the direction of change, the processing device is further configured to assign, to a given weight of the plurality of weights, the direction of change based on a number of times that the given weight changed according to the direction of change during training of the neural network model. ### Claim 12 (depends on 10) The apparatus of claim 10, wherein, to calculate, for each weight of the plurality of weights, the direction of change, the processing device is further configured to assign, to a given weight of the plurality of weights, the direction of change based on a delta between a first value for the given weights and a last value for the given weight during training of the neural network model. ### Claim 13 (depends on 8) The apparatus of claim 8, wherein to calculate the plurality of quantized weights, the processing device is configured to: select a subset of the plurality of weights based on the importance metric; cluster the subset of the plurality of weights into a plurality of clusters; map each weight of the subset of the plurality of weights to a centroid of a corresponding cluster of the plurality of clusters; and map each weight of a remainder of the plurality of weights to a nearest centroid based on a corresponding direction of change. ### Claim 14 (depends on 8) The apparatus of claim 8, wherein to calculate the plurality of quantized weights, the processing device is configured to: initialize, for the plurality of weights, a plurality of centroids; scale, based on the importance metric, a distance for each weight of the plurality of weights to the plurality of centroids; update the plurality of centroids based on a scaled distance for each weight of the plurality of weights; and map each weight of the plurality of weights to a nearest centroid of the updated plurality of centroids. ### Claim 15 A non-transitory computer readable storage medium storing instructions which, when executed, cause a processing device to: determine, during training of a neural network model, for each of a plurality of training iterations, a corresponding value for a plurality of weights; calculate, for each weight of the plurality of weights and based on the corresponding value for each of the plurality of weights, an importance metric; calculate a plurality of quantized weights by binning the plurality of weights based on the importance metric; and update the neural network model based on the plurality of quantized weights. ### Claim 16 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein the importance metric comprises a coefficient of variation. ### Claim 17 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein the processing device is further configured to calculate, for each weight of the plurality of weights, a direction of change. ### Claim 18 (depends on 17) The non-transitory computer readable storage medium of claim 17, wherein, to calculate, for each weight of the plurality of weights, the direction of change, the instructions, when executed, cause the processing device to assign, to a given weight of the plurality of weights, the direction of change based on a number of times that the given weight changed according to the direction of change during training of the neural network model. ### Claim 19 (depends on 17) The non-transitory computer readable storage medium of claim 17, wherein, to calculate, for each weight of the plurality of weights, the direction of change, the instructions, when executed, cause the processing device to assign, to a given weight of the plurality of weights, the direction of change based on a delta between a first value for the given weights and a last value for the given weight during training of the neural network model. ### Claim 20 (depends on 15) The non-transitory computer readable storage medium of claim 15, wherein to calculate the plurality of quantized weights, the instructions, when executed, cause the processing device to: select a subset of the plurality of weights based on the importance metric; cluster the subset of the plurality of weights into a plurality of clusters; map each weight of the subset of the plurality of weights to a centroid of a corresponding cluster of the plurality of clusters; and map each weight of a remainder of the plurality of weights to a nearest centroid based on a corresponding direction of change.