Infinite Recommendation Networks: A Data-Centric Approach

Noveen Sachdeva, Mehak Preet Dhaliwal, Carole-Jean Wu, Julian McAuley

Keywords: Dataset Distillation, NTK, Data-centric AI, Recommender Systems

TL;DR: Is more data what you need for performing accurate recommendation? We build NTK-based models that can get SoTA results using 2-3 orders of magnitude lesser data

Abstract: We leverage the Neural Tangent Kernel and its equivalence to training infinitely-wide neural networks to devise $\infty$-AE: an autoencoder with infinitely-wide bottleneck layers. The outcome is a highly expressive yet simplistic recommendation model with a single hyper-parameter and a closed-form solution. Leveraging $\infty$-AE's simplicity, we also develop Distill-CF for synthesizing tiny, high-fidelity data summaries which distill the most important knowledge from the extremely large and sparse user-item interaction matrix for efficient and accurate subsequent data-usage like model training, inference, architecture search, etc. This takes a data-centric approach to recommendation, where we aim to improve the quality of logged user-feedback data for subsequent modeling, independent of the learning algorithm. We particularly utilize the concept of differentiable Gumbel-sampling to handle the inherent data heterogeneity, sparsity, and semi-structuredness, while being scalable to datasets with hundreds of millions of user-item interactions. Both of our proposed approaches significantly outperform their respective state-of-the-art and when used together, we observe $96-105$% of $\infty$-AE's performance on the full dataset with as little as $0.1$% of the original dataset size, leading us to explore the counter-intuitive question: Is more data what you need for better recommendation?

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:2206.02626/code)