CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process

TL;DR

A novel CDR framework with neural process (NP) that develops the meta-learning paradigm to leverage user-specific preference, and introduces a stochastic process by NP to capture the preference correlations among the overlapping and cold-start users, thus generating more powerful mapping functions by mapping the user-specific preference and common preference correlations to a predictive probability distribution.

Abstract

Cross-domain recommendation (CDR) has been proven as a promising way to tackle the user cold-start problem, which aims to make recommendations for users in the target domain by transferring the user preference derived from the source domain. Traditional CDR studies follow the embedding and mapping (EMCDR) paradigm, which transfers user representations from the source to target domain by learning a user-shared mapping function, neglecting the user-specific preference. Recent CDR studies attempt to learn user-specific mapping functions in meta-learning paradigm, which regards each user's CDR as an individual task, but neglects the preference correlations among users, limiting the beneficial information for user representations. Moreover, both of the paradigms neglect the explicit user-item interactions from both domains during the mapping process. To address the above issues, this paper proposes a novel CDR framework with neural process (NP), termed as CDRNP. Particularly, it develops the meta-learning paradigm to leverage user-specific preference, and further introduces a stochastic process by NP to capture the preference correlations among the overlapping and cold-start users, thus generating more powerful mapping functions by mapping the user-specific preference and common preference correlations to a predictive probability distribution. In addition, we also introduce a preference remainer to enhance the common preference from the overlapping users, and finally devises an adaptive conditional decoder with preference modulation to make prediction for cold-start users with items in the target domain. Experimental results demonstrate that CDRNP outperforms previous SOTA methods in three real-world CDR scenarios.

Figures (6)

• Figure 1: Users 1 and 2 are overlapping users, while User 3 is a cold-start user. (a) The framework of EMCDR-based methods by learning a user-shared mapping function. (b) The framework of meta-learning-based CDR methods by learning user-specific mapping functions. (c) The framework of our CDRNP by capturing preference correlations among users.
• Figure 2: An illustration of our model CDRNP with NP in the training and testing phase.
• Figure 3: The framework of CDRNP in the training phase. The characteristic embedding layer is used to generate $\bm{x}_m^o$. Both of the $\mathcal{C}_i$ and $\mathcal{Q}_i$ are encoded to generate the variational prior and posterior. $\bm{h}_i$ learned from the preference remainer is used to modulate the decoder parameters. $\bm{z}_i$ sampled from $q(\bm{z}_i|\mathcal{Q}_i)$ is concatenated with $\bm{x}_m^o$ in $\mathcal{Q}_i$ to predict ${\hat{y}_m^t}$ for $\mathcal{Q}_i$ via decoder.
• Figure 4: Performance comparison of CDR to cold-start users with different lengths of interaction items history $\mathcal{V}^{s}(u_j)$.
• Figure 5: Performance comparison of CDR for cold-start users with different lengths of support set $\mathcal{C}_i$.