Disentangled Representation Learning for Recommendation

Abstract

Disentangled Representation Learning (DRL) aims to learn a model capable of identifying and disentangling the underlying factors hidden in the observable data in representation form. The process of separating underlying factors of variation into variables with semantic meaning benefits in learning explainable representations of data, which imitates the meaningful understanding process of humans when observing an object or relation. As a general learning strategy, DRL has demonstrated its power in improving the model explainability, controlability, robustness, as well as generalization capacity in a wide range of scenarios such as computer vision, natural language processing, data mining etc. In this article, we comprehensively review DRL from various aspects including motivations, definitions, methodologies, evaluations, applications and model designs. We discuss works on DRL based on two well-recognized definitions, i.e., Intuitive Definition and Group Theory Definition. We further categorize the methodologies for DRL into four groups, i.e., Traditional Statistical Approaches, Variational Auto-encoder Based Approaches, Generative Adversarial Networks Based Approaches, Hierarchical Approaches and Other Approaches. We also analyze principles to design different DRL models that may benefit different tasks in practical applications. Finally, we point out challenges in DRL as well as potential research directions deserving future investigations. We believe this work may provide insights for promoting the DRL research in the community.

Disentangled Partial Label Learning

“…Specifically, the learned representation are expected to isolate information about each specific factor in only a few (or a group of) dimensions. Benefiting from separating out the underlying structure of the data into disjoint parts, disentangled representation is inherently more interpretable, robust to adversarial attack and capable of enhancing the gen-eralization ability of learning systems (Wang et al 2023b;Steenkiste et al 2019;Reddy, Godfrey, and Balasubramanian 2022;Ma et al 2019).…”

Unsupervised Domain Adaptation Semantic Segmentation of High-Resolution Remote Sensing Imagery With Invariant Domain-Level Prototype Memory

“…Existing studies [58,59] have demonstrated the potential of DRL in modeling human learning and understanding of the world, mainly because DRL encourages the representations to carry interpretable semantic information with independent factors, and shows significant potential for representing invariance [60,61], integrity [62,63], and generalization [64,65]. In view of this, CRL is now widely applied in computer vision [66][67][68][69][70], natural language processing [71][72][73][74][75], and graphical learning [76][77][78]. The most typical approaches of DRL are based on generative models such as variational auto-encoder (VAE) [79] or generative adversarial network (GAN) [80].…”

Multimodal Recommender Systems: A Survey

“…The multimodal features are fed into different modality encoders. The modality encoders extract the representations and are general architectures used in other fields, such as ViT [13] for images and General [34] Coarse-grained Attention CL [40] Coarse-grained Attention None [6], [21] Fine-gained Attention None [30], [27], [57] Combined Attention None [44], [39] User-item Graph + Fine-gained Attention None [56] User-item Graph CL [59] Item-item Graph CL [58], [38] Item-item Graph None [33] Item-item Graph + Fine-gained Attention None [50], [45] Knowledge Graph None [2], [46] Knowledge Graph CL [8] Knowledge Graph + Fine-gained Attention None [43] Knowledge Graph + Filtration (graph) None [63], [55], [31] Filtration (graph) None [49], [4] MLP / Concat DRL [15], [28] Fine-gained Attention DRL [61], [36], [48] None DRL…”

“…Besides, contrastive learning guarantees the consistency and gap between separated modal representations. Compared with MacridVAE, SEM-MacridVAE [48] considers item semantic information when learning disentangled representations from user behaviors.…”