IP Library Granted Patent US 11,526,765
Granted Patent B2
US 11,526,765 · App. 16/740,072 · Granted Dec 13, 2022

Systems and methods for a supra-fusion graph attention model for multi-layered embeddings and deep learning applications

Inventors: Uday Shanthamallu (Tempe, AZ); Jayaraman Thiagarajan (Dublin, CA); Andreas Spanias (Tempe, AZ); Huan Song (Tempe, AZ)
Assignees: Arizona Board of Regents on Behalf of Arizona State University; Lawrence Livermore National Security, LLC
G06N3/084G06F16/9024G06F17/16G06N3/04
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,526,765
App. No.
16/740,072
Granted
Dec 13, 2022
Kind
B2
Abstract

Various embodiments of systems and methods for attention models with random features for multi-layered graph embeddings are disclosed.

Claims (11)

1. A method, comprising:

providing a multi-layered graph having a plurality of graph layers, each of the plurality of graph layers including a plurality of nodes;

constructing a graph-layer-specific latent feature vector for each of the plurality of nodes using a graph-layer-specific attention model;

inferring dependencies between nodes of the plurality of nodes by processing all sets of graph-layer-specific features using a supra-fusion layer, wherein the supra-fusion layer comprises a plurality of fusion heads;

obtaining a consensus representation from each of the plurality of fusion heads using an overall fusion head, wherein each of the plurality of fusion heads of the supra-fusion layer performs a weighted combination of the graph-layer-specific latent feature vectors for a node from each of a plurality of graph-layer-specific attention heads, and wherein each of the plurality of fusion heads comprises a scaling factor associated with each of the plurality of graph-layer-specific attention heads, wherein each of the scaling factors are shared across each of the plurality of nodes; and

characterizing each node of the plurality of nodes by aggregating layer-specific node features associated with one node of the plurality of nodes across each of a plurality of attention layers.

2. The method of claim 1 , further comprising:

generating a set of random attributes for every node in the graph layer using random initialization.

3. The method of claim 1 , wherein the graph-layer-specific attention model is restricted to a single graph layer.

4. The method of claim 1 , further comprising:

processing each output of the supra-fusion layer using a feed-forward layer.

Assignments (5)
CONFIRMATORY LICENSE Recorded Jan 25, 2023
From: LAWRENCE LIVERMORE NATIONAL SECURITY, LLC
To: U.S. DEPARTMENT OF ENERGY
Reel/Frame 062486/0082 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 1, 2021
From: THIAGARAJAN, JAYARAMAN
To: LAWRENCE LIVERMORE NATIONAL SECURITY, LLC
Reel/Frame 055803/0051 →
CONFIRMATORY LICENSE (SEE DOCUMENT FOR DETAILS) Recorded Jul 21, 2020
From: LAWRENCE LIVERMORE NATIONAL SECURITY, LLC
To: U.S. DEPARTMENT OF ENERGY
Reel/Frame 053267/0738 →
CONFIRMATORY LICENSE Recorded Jul 13, 2020
From: ARIZONA STATE UNIVERSITY, TEMPE
To: NATIONAL SCIENCE FOUNDATION
Reel/Frame 053190/0501 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 29, 2020
From: SHANTHAMALLU, UDAY; SPANIAS, ANDREAS; SONG, HUAN
To: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITY
Reel/Frame 051657/0533 →
Continuity (2)
Provisional Application 62790830 · Jan 10, 2019
Related Publication 20200226472A1 · Jul 16, 2020