Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

An illustrative diagram shows how to use MIRN in an industrial recommendation system.

MIRN focuses on the matching stage, which aims to retrieve user-interested items efficiently. Note that the matching stage is concerned with retrieving good items, rather than specific item ranks.

More »

Fig 1 Expand

Table 1.

Glossary.

More »

Table 1 Expand

Fig 2.

Network structure of MIRN.

MIRN takes a sequence of user profile features and user behaviors as input and outputs multiple user representation vectors for item retrieval. User behaviors and other user features (gender, age, etc.) are fed to the multi-interest representation learning module through the corresponding operations (feature embedding and average pooling) of the embedding module. Then, the interest Capsules generated by the multi-interest representation learning module are stitched with the user’s other feature embeddings separately, and multiple user representation vectors are obtained through several Full connection & ReLU layers. Finally, multiple user representation vectors are used in parallel for Top N item retrieval. The Capsule-aware module is mainly used to guide the training of the model.

More »

Fig 2 Expand

Table 2.

Statistics of the two datasets for offline evaluation.

More »

Table 2 Expand

Table 3.

Performance comparison of different models on publicly available datasets.

More »

Table 3 Expand

Table 4.

Performance comparison of different models on other Amazon datasets.

More »

Table 4 Expand

Fig 3.

Comparison of HR@50 performance between our model and other models on different datasets.

More »

Fig 3 Expand

Table 5.

Model performance for different parameters .

More »

Table 5 Expand

Fig 4.

Performance comparison of different numbers of interest in MIRN.

The y-axis represents the value of HR@50 and the x-axis gives the number of iterations. MIRN performs better with bigger .

More »

Fig 4 Expand

Fig 5.

Heatmap of coupling coefficients for user behaviors.

Each behavior has a corresponding coupling coefficient in the corresponding capsule of interest.

More »

Fig 5 Expand

Table 6.

Comparison of the speed and accuracy of different dense retrieval models on Amazon Electron.

More »

Table 6 Expand