CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data

TL;DR

CERES is a graph-conditioned transformer model pretrained on large-scale session data, effectively capturing intra-item semantics and inter-item relations to improve session-based search and linking tasks.

Contribution

Introduces CERES, a novel graph-based transformer for semi-structured session data, combining graph-conditioned masked language modeling and transformer architecture.

Findings

CERES outperforms baselines by up to 9% in session search tasks.

Pretrained on 468 million Amazon sessions.

Effectively captures intra- and inter-item semantics.

Abstract

User sessions empower many search and recommendation tasks on a daily basis. Such session data are semi-structured, which encode heterogeneous relations between queries and products, and each item is described by the unstructured text. Despite recent advances in self-supervised learning for text or graphs, there lack of self-supervised learning models that can effectively capture both intra-item semantics and inter-item interactions for semi-structured sessions. To fill this gap, we propose CERES, a graph-based transformer model for semi-structured session data. CERES learns representations that capture both inter- and intra-item semantics with (1) a graph-conditioned masked language pretraining task that jointly learns from item text and item-item relations; and (2) a graph-conditioned transformer architecture that propagates inter-item contexts to item-level representations. We pretrained CERES using ~468 million Amazon sessions and find that CERES outperforms strong pretraining baselines by up to 9% in three session search and entity linking tasks.