RECORD
Deep Unified Representation for Heterogeneous Recommendation
Information Retrieval · Submitted 15 Jan 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experimental results demonstrate that with the unified representation, our model achieves remarkable improvement (e.g., 4.1% ~ 34.9% lift by AUC score and 3.7% lift by online CTR) over existing state-of-the-art models.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Recommendation system has been a widely studied task both in academia and industry. Previous works mainly focus on homogeneous recommendation and little progress has been made for heterogeneous recommender systems. However, heterogeneous recommendations, e.g., recommending different types of items including products, videos, celebrity shopping notes, among many others, are dominant nowadays. State-of-the-art methods are incapable of leveraging attributes from different types of items and thus suffer from data sparsity problems. And it is indeed quite challenging to represent items with different feature spaces jointly. To tackle this problem, we propose a kernel-based neural network, namely deep unified representation (or DURation) for heterogeneous recommendation, to jointly model unified representations of heterogeneous items while preserving their original feature space topology structures. Theoretically, we prove the representation ability of the proposed model. Besides, we conduct extensive experiments on real-world datasets. Experimental results demonstrate that with the unified representation, our model achieves remarkable improvement (e.g., 4.1% ~ 34.9% lift by AUC score and 3.7% lift by online CTR) over existing state-of-the-art models.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Recommendation system has been a widely studied task both in academia and industry. | background 1.00 | 0.04 | 0.01 | asserted 1.00 |
| s1 | Previous works mainly focus on homogeneous recommendation and little progress has been made for heterogeneous recommender systems. | gap 0.94 | 0.05 | 0.02 | asserted 1.00 |
| s2 | However, heterogeneous recommendations, e.g., recommending different types of items including products, videos, celebrity shopping notes, among many others, are dominant nowadays. | background 0.91 | 0.06 | 0.03 | asserted 1.00 |
| s3 | State-of-the-art methods are incapable of leveraging attributes from different types of items and thus suffer from data sparsity problems. | gap 0.85 | 0.07 | 0.03 | asserted 1.00 |
| s4 | And it is indeed quite challenging to represent items with different feature spaces jointly. | background 0.86 | 0.06 | 0.02 | asserted 1.00 |
| s5 | To tackle this problem, we propose a kernel-based neural network, namely deep unified representation (or DURation) for heterogeneous recommendation, to jointly model unified representations of heterogeneous items while preserving their original feature space topology structures. | method 0.52 | 0.94 | 0.14 | asserted 0.99 |
| s6 | Theoretically, we prove the representation ability of the proposed model. | contribution 0.96 | 0.95 | 0.04 | asserted 1.00 |
| s7 | Besides, we conduct extensive experiments on real-world datasets. | method 0.65 | 0.95 | 0.03 | asserted 0.97 |
| s8 | Experimental results demonstrate that with the unified representation, our model achieves remarkable improvement (e.g., 4.1% ~ 34.9% lift by AUC score and 3.7% lift by online CTR) over existing state-of-the-art models. | result 1.00 | 0.97 | 0.87 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Recommendation system has been a widely studied task both in academia and industry. Previous works mainly focus on homogeneous recommendation and little progress has been made for heterogeneous recommender systems. However, heterogeneous recommendations, e.g., recommending different types of items including products, videos, celebrity shopping notes, among many others, are dominant nowadays. State-of-the-art methods are incapable of leveraging attributes from different types of items and thus suffer from data sparsity problems. And it is indeed quite challenging to represent items with different feature spaces jointly. To tackle this problem, we propose a kernel-based neural network, namely deep unified representation (or DURation) for heterogeneous recommendation, to jointly model unified representations of heterogeneous items while preserving their original feature space topology structures. Theoretically, we prove the representation ability of the proposed model. Besides, we conduct extensive experiments on real-world datasets. Experimental results demonstrate that with the unified representation, our model achieves remarkable improvement (e.g., 4.1% ~ 34.9% lift by AUC score and 3.7% lift by online CTR) over existing state-of-the-art models.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 3 sentences without a confident label
Cites as support 1 paper
-
Besides, lack of feature distribution alignments can lead to overfitting when data is sparse [ref] .
Adversarial Feature Distribution Alignment for Semi-Supervised Learning · Alignment · 0.97
Cites as background 1 paper
-
With the development of deep learning, recent works start to utilize deep neural network as the feature extractor to learn representations from both interaction and attribute features [ref] .
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction · Related Work · 0.88
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.