Shared update scheme improves personalized predictions and content generation

Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization

Machine Learning

Summary

People interact with many kinds of content like movies, news, and chats, each having different actions and results. The authors studied if a single method can update a user’s memory from all these different interactions. They created a system that treats actions linked to content in a common way and showed it works well across different tasks like predicting news or creating personalized headlines. Their method can also transfer what it learns from one type of content to another, improving recommendations even when trained elsewhere.

What this means in practice

  • For news recommendation teams: Use a unified update mechanism to improve personalized news suggestions and headline creation from varied user interactions.
  • For streaming service engineers: Transfer a trained user update core from one content domain to enhance movie recommendation accuracy with less retraining.

Authors

Parthiv Chatterjee, Kashish Kanjaria, Vashisth Purani, Sourish Dasgupta, Tanmoy Chakraborty

Abstract

A user's movie, news, and dialogue histories differ in their native actions and outputs, yet each interaction supplies evidence that can update user memory. We study whether these histories can train one reusable update mechanism. An action-on-item schema pairs a mapped interaction role with a content embedding, allowing shared update parameters to operate on separate user states. We establish invariance to native relabeling, bounded state changes under item-embedding perturbations, and a pooled-training bound under explicit compatibility conditions. The Multi-Timescale State Hypothesis (MTSH) specifies how this evidence enters, persists, and is consumed; PerTIDE implements it with action gating, three state-space traces, fusion, and command-conditioned readout. On PENS, the same history encoder supports both next-news prediction and personalized headline generation. In a controlled PENS-to-MovieLens experiment, a frozen source-trained core exceeds an identically structured random core by 15.23 MRR points after fitting the same target consumer. On MIND, PerTIDE retains a 4.12-point MRR advantage over a same-input three-branch state-space control. Action, readout, and trace interventions identify complementary contributions to these gains. Together, the theory and experiments support learning history updates across compatible sources and reusing them through predictive and generative consumers.