Joint Group Profiling and Recommendation via Deep Neural Network-based Multi-Task Learning
Ngoc Luyen Le, Marie-Hélène Abel
TL;DR
This work tackles the challenge of group recommender systems by jointly optimizing group profiling and group-level recommendations through a deep neural network-based multi-task learning framework. The model uses individual user features, attention over group members, and a shared representation to produce a latent group profile and accurate item recommendations, with a dual objective loss $\mathcal{L} = \mathcal{L}_{rec} + \lambda \mathcal{L}_{profile}$. Empirical results on ITM-Rec and MovieLens 100K demonstrate that the proposed Deep Multi-Task Learning (DMTL) approach outperforms traditional baselines in both profiling accuracy (Precision, Recall, F1) and top-$K$ recommendation quality (P@10, R@10), confirming the benefit of shared representations and task synergy. The findings suggest practical impact for real-world group decision-making scenarios and point to future work integrating unstructured data and scalable training for real-time group recommendations.
Abstract
Group recommender systems aim to generate recommendations that align with the collective preferences of a group, introducing challenges that differ significantly from those in individual recommendation scenarios. This paper presents Joint Group Profiling and Recommendation via Deep Neural Network-based Multi-Task Learning, a framework that unifies group profiling and recommendation tasks within a single model. By jointly learning these tasks, the model develops a deeper understanding of group dynamics, leading to improved recommendation accuracy. The shared representations between the two tasks facilitate the discovery of latent features essential to both, resulting in richer and more informative group embeddings. To further enhance performance, an attention mechanism is integrated to dynamically evaluate the relevance of different group features and item attributes, ensuring the model prioritizes the most impactful information. Experiments and evaluations on real-world datasets demonstrate that our multi-task learning approach consistently outperforms baseline models in terms of accuracy, validating its effectiveness and robustness.