Get the newsletter
Qualcomm · AI / ML · Filed Mar 26, 2025 · USPTO published Oct 1, 2026 · Oct 1 release

Qualcomm Patents a Way to Train AI Models Across Many Phones at Once

Training an AI model usually means sending huge amounts of data to a central server. Qualcomm's new patent sketches out a way to do that training across many phones at the same time, using the wireless signal itself to do part of the math.

A wireless communication network connects various devices, including phones, cars, and drones, to cell towers and data centers for distributed machine learning. Drawing from patent filing US 2026/0304221 A1.
A wireless communication network connects various devices, including phones, cars, and drones, to cell towers and data centers for distributed machine learning.All 13 drawings ↓
Publication number
US 2026/0304221 A1(US20260304221A1)
Applicant
QUALCOMM Incorporated
Filed · Published
Mar 26, 2025 · Oct 1, 2026
Inventors
Yuval BEN HUR, Evgeny LEVITAN, Ariel Yaakov SAGI, Amit MOSES, Ronen SHAKED, Gideon Shlomo KUTZ
Status when we published
Waiting for an examiner
Document
20 claims
US classification
370/329

How Qualcomm trains AI across phones without clogging the network

Ever tried to stream a video while a hundred other people on your block are doing the same thing? The network buckles. Now imagine trying to train an AI model across thousands of phones simultaneously, each sending its own data back to a server. That's an even harder problem, and it's what this patent is trying to solve.

Qualcomm's approach lets a group of phones each do a small piece of the AI training work locally, compress the results, and then transmit those compressed results at the same time on the same wireless channel. The clever part: the signals from all those phones overlap in the air and automatically add up at the receiving end, which is the base station or network equipment. The network gets one combined result rather than thousands of separate messages.

This matters most for a style of AI training called federated learning, where your phone contributes to improving a shared model without ever sending your raw personal data to a central server. Your data stays on your device; only heavily compressed math summaries leave it.

From the filing · CLAIM 1
… transmit, to the plurality of UEs, an indication of a wireless communication resource to be used by the plurality of UEs for concurrent transmission of compressed gradient data that is compressed using the linear compression matrix; …

Translation: The server tells multiple phones to send their compressed training data at the same time using specific radio channels.

How the linear compression matrix shrinks gradient traffic

The patent describes a system built around three moving parts: the network equipment (what the patent calls a network entity, think a cell tower's brain), a group of phones (user equipments or UEs), and a shared linear compression matrix.

Here is how a training round works:

  • The network sends each phone the same compression matrix, essentially a set of math rules for shrinking data.
  • Each phone runs a piece of the AI training locally, producing gradient data (the tiny nudges that tell a model which direction to improve).
  • Each phone multiplies its gradient data by the compression matrix, making the payload much smaller, then transmits on a shared wireless slot simultaneously with every other phone in the group.
  • Because the phones broadcast at the same time on the same channel, their signals stack up in the air. The base station receives one combined signal, an over-the-air (OTA) summation, which is mathematically equivalent to summing all the individual compressed gradients.

The network then either relays that summed result back to the phones or uses it to compute a model update and push that update out instead. The compression step is linear, meaning it uses straightforward matrix multiplication rather than a learned or nonlinear encoder, which keeps the math predictable and reversible.

The key efficiency gain is that over-the-air aggregation sidesteps the need to collect, store, and add up thousands of separate messages in software. The wireless channel does the addition for free, as a physical property of how radio waves combine.

From the filing · THE ABSTRACT
… receive, via the wireless communication resource, a first signal including an over-the-air (OTA) summation of the compressed gradient data.

Translation: The system combines all the phones' training updates directly in the air as they are received simultaneously.

What this means for AI trained on your private phone data

For everyday users, federated learning is one of the more privacy-friendly ways to improve AI features on your phone, things like predictive text, on-device voice recognition, or photo tagging, without those improvements requiring your personal files to leave the device. This patent pushes that idea further by making the process fast enough to work inside a standard cellular network's timing and bandwidth constraints.

On the engineering side, the compression step is what makes this realistic. Gradient data is normally large, and sending it uncompressed from thousands of phones would eat up spectrum quickly. By agreeing on a shared compression matrix upfront, Qualcomm's system trades a small amount of accuracy for a large reduction in data volume, a tradeoff that wireless AI training almost always requires. Qualcomm's run of federated-learning filings suggests this is a sustained area of investment, not a one-off.

Qualcomm's 17th filing we've tracked since July in our on-device AI privacy watch builds on earlier ideas around cross-device identity checks and peer-to-peer AI training.

Source: US 2026/0304221 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Qualcomm patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 13 sheets

13 drawing sheets from US 2026/0304221 A1 · click any drawing to enlarge

Wireless network with connected devices., drawing sheet 1 from US 2026/0304221 A1
Sheet 1 Wireless network with connected devices.
Phones sending compressed data to cell tower., drawing sheet 2 from US 2026/0304221 A1
Sheet 2 Phones sending compressed data to cell tower.
Cell tower coordinating phone data., drawing sheet 3 from US 2026/0304221 A1
Sheet 3 Cell tower coordinating phone data.
Communications manager in a device., drawing sheet 4 from US 2026/0304221 A1
Sheet 4 Communications manager in a device.
Communications manager with compression and summation., drawing sheet 5 from US 2026/0304221 A1
Sheet 5 Communications manager with compression and summation.
Components for managing wireless communication., drawing sheet 6 from US 2026/0304221 A1
Sheet 6 Components for managing wireless communication.
Device with processor, memory, and transceiver., drawing sheet 7 from US 2026/0304221 A1
Sheet 7 Device with processor, memory, and transceiver.
Receiver, manager, and transmitter in a device., drawing sheet 8 from US 2026/0304221 A1
Sheet 8 Receiver, manager, and transmitter in a device.
Show the other 5 sheets
Qualcomm Patents a Way to Train AI Models Across Many Phones at Once patent drawing, sheet 9
Sheet 9
Qualcomm Patents a Way to Train AI Models Across Many Phones at Once patent drawing, sheet 10
Sheet 10
Qualcomm Patents a Way to Train AI Models Across Many Phones at Once patent drawing, sheet 11
Sheet 11
Qualcomm Patents a Way to Train AI Models Across Many Phones at Once patent drawing, sheet 12
Sheet 12
Qualcomm Patents a Way to Train AI Models Across Many Phones at Once patent drawing, sheet 13
Sheet 13
Patent filing page

More in AI training & infrastructure

All 323 AI training & infrastructure patents →

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.