# Task-adaptive Neural Process for User Cold-Start Recommendation

arXiv: https://arxiv.org/abs/2103.06137 · HTML: https://mlsanity.com/paper/2103.06137/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2021.

## Built on by (most cited first, 30 of 32)

- [LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2302.08191/) (2023)
- [GraphEdit: Large Language Models for Graph Structure Learning](https://mlsanity.com/paper/2402.15183/) (2024)
- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2304.08183/) (2023)
- [Robust Inverse Framework using Knowledge-guided Self-Supervised Learning: An application to Hydrology](https://mlsanity.com/paper/2109.06429/) (2021)
- [Dynamic Graph Unlearning: A General and Efficient Post-Processing Method via Gradient Transformation](https://mlsanity.com/paper/2405.14407/) (2024)
- [Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs](https://mlsanity.com/paper/2211.08568/) (2022)
- [Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation](https://mlsanity.com/paper/2306.14462/) (2023)
- [EasyRec: Simple yet Effective Language Models for Recommendation](https://mlsanity.com/paper/2408.08821/) (2024)
- [Memory Efficient Neural Processes via Constant Memory Attention Block](https://mlsanity.com/paper/2305.14567/) (2023)
- [Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations](https://mlsanity.com/paper/2204.00327/) (2022)
- [Entity Aware Modelling: A Survey](https://mlsanity.com/paper/2302.08406/) (2023)
- [ColdNAS: Search to Modulate for User Cold-Start Recommendation](https://mlsanity.com/paper/2306.03387/) (2023)
- [Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach](https://mlsanity.com/paper/2307.01204/) (2023)
- [PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction](https://mlsanity.com/paper/2310.00614/) (2023)
- [IDNP: Interest Dynamics Modeling using Generative Neural Processes for Sequential Recommendation](https://mlsanity.com/paper/2208.04600/) (2022)
- [Knowledge-Driven New Drug Recommendation](https://mlsanity.com/paper/2210.05572/) (2022)
- [All-in-One: Heterogeneous Interaction Modeling for Cold-Start Rating Prediction](https://mlsanity.com/paper/2403.17740/) (2024)
- [Learning Social Graph for Inactive User Recommendation](https://mlsanity.com/paper/2405.05288/) (2024)
- [R'enyi Neural Processes](https://mlsanity.com/paper/2405.15991/) (2024)
- [LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters](https://mlsanity.com/paper/2405.16287/) (2024)
- [Modeling Churn in Recommender Systems with Aggregated Preferences](https://mlsanity.com/paper/2502.18483/) (2025)
- [Compositional Meta-Learning for Mitigating Task Heterogeneity in Physics-Informed Neural Networks](https://mlsanity.com/paper/2604.26999/) (2026)
- [MultiHead MultiModal Deep Interest Recommendation Network](https://mlsanity.com/paper/2110.10205/) (2021)
- [Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up](https://mlsanity.com/paper/2302.14395/) (2023)
- [ClusterSeq: Enhancing Sequential Recommender Systems with Clustering based Meta-Learning](https://mlsanity.com/paper/2307.13766/) (2023)
- [Privacy Challenges in Meta-Learning: An Investigation on Model-Agnostic Meta-Learning](https://mlsanity.com/paper/2406.00249/) (2024)
- [Graph Contrastive Learning for Optimizing Sparse Data in Recommender Systems with LightGCL](https://mlsanity.com/paper/2506.00048/) (2025)
- [Churn-Aware Recommendation Planning under Aggregated Preference Feedback](https://mlsanity.com/paper/2507.04513/) (2025)
- [Deep Graph Neural Point Process For Learning Temporal Interactive Networks](https://mlsanity.com/paper/2508.13219/) (2025)

## Abstract (arXiv)

User cold-start recommendation is a long-standing challenge for recommender systems due to the fact that only a few interactions of cold-start users can be exploited. Recent studies seek to address this challenge from the perspective of meta learning, and most of them follow a manner of parameter initialization, where the model parameters can be learned by a few steps of gradient updates. While these gradient-based meta-learning models achieve promising performances to some extent, a fundamental problem of them is how to adapt the global knowledge learned from previous tasks for the recommendations of cold-start users more effectively. In this paper, we develop a novel meta-learning recommender called task-adaptive neural process (TaNP). TaNP is a new member of the neural process family, where making recommendations for each user is associated with a corresponding stochastic process. TaNP directly maps the observed interactions of each user to a predictive distribution, sidestepping some training issues in gradient-based meta-learning models. More importantly, to balance the trade-off between model capacity and adaptation reliability, we introduce a novel task-adaptive mechanism. It enables our model to learn the relevance of different tasks and customize the global knowledge to the task-related decoder parameters for estimating user preferences. We validate TaNP on multiple benchmark datasets in different experimental settings. Empirical results demonstrate that TaNP yields consistent improvements over several state-of-the-art meta-learning recommenders.