Content-Collaborative Disentanglement Representation Learning for - - PowerPoint PPT Presentation

Content-Collaborative Disentanglement Representation Learning for Enhanced Recommendation

YinZhangZiweiZhuYunHeJamesCaverlee

Department of Computer Science and Engineering Texas A&M University, USA

Collaborative features vs Content features

Collaborative Filtering Content-aware Recommendation

Dress content info User content info Image, Descriptions, Reviews, … Age, Jobs, Social Connections, …

?

What if we consider both Collaborative features and Content features?

Item Content Information

What if we consider both Collaborative features and Content features?

Many similar users prefer the dress because of: The dress image is the known content information

• Dress Appearances
• Dress Price
• Dress Quality

Item Content Information

What if we consider both Collaborative features and Content features?

Many similar users prefer the dress because of:

• Dress Appearances
• Dress Price
• Dress Quality

Item Content Information

The dress image is the known content information

What if we consider both Collaborative features and Content features?

Many similar users prefer the dress because of:

• Dress Appearances
• Dress Price
• Dress Quality

Feature Duplication High Feature Correlation

Item Content Information

The dress image is the known content information

Collaborative features vs Content features

Learning user preferences based on both content-based features and collaborative features can be problematic:

Our Goal: Learn disentangled representations from user behavior data and content information

Feature Duplication High Feature Correlation

• 1. Limiting the representation capability
• 2. Overweighting these correlated features

Disentangled Representation Learning

• Aims to identify each feature that is relatively not influenced by other

feature changes

We want to learn the features:

https://ai.googleblog.com/2019/04/evaluating-unsupervised-learning-of.html

• High quality representation; Robust performance; Interpretability
• shape;
• color;
• object position;

relatively not influence each

• ther changes
• Commonly used method: statistically independent [1]

[1] Chen, Ricky TQ, et al. "Isolating sources of disentanglement in variational autoencoders." Advances in Neural Information Processing Systems. 2018.

How to learn disentangled features from both content and collaborative information? Challenges

• 1. High heterogeneity between implicit features in user-item interactions and

explicit features in content information

Disentangled?

• 2. Granular-level disentanglement

(disentanglement within features)

Disentangled

How to learn disentangled features from both content and collaborative information? Challenges

• 1. High heterogeneity between implicit features in user-item interactions and

explicit features in content information

Disentangled?

• 2. Granular-level disentanglement

(disentanglement within features)

Disentangled Collaborative features Content features Disentangled? Disentangled?

Proposed Method: DICER

We propose a novel two-level disentanglement approach called DICER – DIsentangling Content-aware collaborative filtering for Enhanced Recommendation – to learn disentangled features considering both content and collaborative features. It contain three steps:

Proposed Method: DICER

We propose a novel two-level disentanglement approach called DICER – DIsentangling Content-aware collaborative filtering for Enhanced Recommendation – to learn disentangled features considering both content and collaborative features. It contain three steps:

• 1. Content-Collaborative disentanglement;

Proposed Method: DICER

We propose a novel two-level disentanglement approach called DICER – DIsentangling Content-aware collaborative filtering for Enhanced Recommendation – to learn disentangled features considering both content and collaborative features. It contain three steps:

• 1. Content-Collaborative disentanglement;
• 2. Feature disentanglement at granular-level;

Proposed Method: DICER

We propose a novel two-level disentanglement approach called DICER – DIsentangling Content-aware collaborative filtering for Enhanced Recommendation – to learn disentangled features considering both content and collaborative features. It contain three steps:

• 1. Content-Collaborative disentanglement;
• 2. Feature disentanglement at granular-level;
• 3. Co-decoders;

Proposed Method: DICER

Content disentangled collaborative features: extracted from user-item interactions Content features: extracted from item content

Content-Collaborative Disentanglement

User feedback x_i is generated from all the features z_i that influence user preference towards items:

(2) We set the extracted features from the content and user-item interactions to be statistically

independent

(1) We decompose z_i to be the content features derived from item content and the content disentangled collaborative features derived from user- item interactions:

Feature Disentanglement

penalizing mutual information through the information bottleneck can encourage feature disentanglement

statistical independence of the learned latent representation in each dimension of z^o under the condition of z^c

ensure the learned latent representations in each dimension are close to their corresponding priors

Disentangle each extracted feature at a granular level —KL decomposition:

Experiments: Recommendation Effectiveness

• DICER consistently outperforms state-of-the-art methods in

recall@K and NDCG@K;

Experiments: Visualization of Content and Collaborative Disentanglement

• By content-collaborative disentanglement in DICER, the learned disentangled content feature

representations and collaborative feature representations capture very different information;

Clustered by item content-oriented info Clustered by user-

• riented info

Conclusions and Future Work

• We propose a novel two-level disentanglement approach that supports both

content-collaborative disentanglement and feature disentanglement based

• n the structure of a variational auto-encoder; 

• We study the relations between content features and collaborative

features, and analyze the potential problem to consider both features at the same time (feature duplication and high correlation);

• By considering the disentanglement between content features and collaborative

features, the learned representations can capture different information and brings large improvement for recommendation.

Future work:

• Extending DICER to other scenarios, e.g., where a user’s social network is available.

Thank you!

Content-Collaborative Disentanglement Representation Learning for Enhanced Recommendation Yin Zhang (zhan13679@tamu.edu)