Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Recommendation algorithm based on adversarial learning and bidirectional long-short-term memory network

A long-short-term memory and recommendation algorithm technology, applied in neural learning methods, biological neural network models, calculations, etc., can solve problems such as the influence of node representation

Inactive Publication Date: 2020-12-04
CHONGQING UNIV
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The reasons for the above limitations are: 1) Both the previous node and the subsequent node on the path may have an impact on the node representation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Recommendation algorithm based on adversarial learning and bidirectional long-short-term memory network
  • Recommendation algorithm based on adversarial learning and bidirectional long-short-term memory network
  • Recommendation algorithm based on adversarial learning and bidirectional long-short-term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0088] see figure 1 , figure 2 , this embodiment discloses a recommendation algorithm based on adversarial learning and two-way long-short-term memory network,

[0089] Specifically include the following steps:

[0090] The first step, pre-defined symbols

[0091] A1) Definition of heterogeneous information network: use the symbol G=(V, E) to represent a heterogeneous information network, where V is a set of nodes, and E is a set of edges;

[0092] A2) Path definition in heterogeneous information network: there is a mapping relationship between each node v and each edge e in the heterogeneous network where T V and T E are node type set and edge type set respectively, T V ≥2 or T E ≥2, U represents the user set, u∈U represents the uth user, there are m users in total, I represents the item set, i∈I represents the i-th item, and there are n items in total;

[0093] A3) In the heterogeneous information network G, define the node connection sequence from user u to item i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a recommendation algorithm based on adversarial learning and a bidirectional long-short-term memory network, which comprises the following steps of: 1, predefining a symbol, including A1) defining a heterogeneous information network, A2) defining a path in the heterogeneous information network, A3) in the heterogeneous information network G, defining a node connection sequence from a user u to an article i as a path, and defining that p = [v1, v2,..., vl], and p belongs to P; and 2, modeling as following: S1, modeling an embedded layer, and representing the embedded layer by using an initialized node vector; S2, constructing a sequence modeling layer, using the vector representation obtained through initialization in the step S1 as input and applying the input to an existing bidirectional LSTM model based on an attention mechanism to optimize vector representation of the node, and learning a coefficient matrix and an offset vector in the model; S3, setting a prediction layer, and finally calculating the probability; and S4, constructing an adversarial learning model. According to the method, the problem of node relation noise in the heterogeneous network isrelieved by learning the adversarial regularization item, adding the adversarial regularization item into a loss function and optimizing the model, the robustness of node embedding is improved, and the recommendation accuracy is ensured.

Description

technical field [0001] The invention relates to the technical field of heterogeneous network recommendation, in particular to a recommendation algorithm based on confrontational learning and bidirectional long-short-term memory network. Background technique [0002] Networks can organize all kinds of data in our lives, such as social networks, biological networks, transportation networks, and so on. Objects and interactions in the real world are often multi-modal and multi-type. To capture and exploit such node and link heterogeneity, heterogeneous networks are proposed and widely used in many practical network mining scenarios, especially in recommender systems. Recommendation models based on heterogeneous networks have attracted extensive attention from researchers because they contain various types of nodes and edges. This type of model can not only alleviate the data sparsity problem in the recommendation system, but also improve the accuracy of the recommendation syst...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/9535G06Q30/06G06K9/62G06N3/04G06N3/08
CPCG06F16/9535G06Q30/0631G06N3/049G06N3/084G06N3/045G06F18/24
Inventor 高旻张峻伟余俊良王宗威熊庆宇赵泉午王旭
Owner CHONGQING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products