Papers › Transformers with multi-modal features and post-fusion context for e-commerce...

Transformers with multi-modal features and post-fusion context for e-commerce session-based recommendation

11 Jul 2021arXiv:2107.05124archive 2025-07-28

Gabriel de Souza P. Moreira, Sara Rabhi, Ronay Ak, Md Yasin Kabir, Even Oldridge

Session-based recommendation is an important task for e-commerce services, where a large number of users browse anonymously or may have very distinct interests for different sessions. In this paper we present one of the winning solutions for the Recommendation task of the SIGIR 2021 Workshop on E-commerce Data Challenge. Our solution was inspired by NLP techniques and consists of an ensemble of two Transformer architectures - Transformer-XL and XLNet - trained with autoregressive and autoencoding approaches. To leverage most of the rich dataset made available for the competition, we describe how we prepared multi-model features by combining tabular events with textual and image vectors. We also present a model prediction analysis to better understand the effectiveness of our architectures for the session-based recommendation.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Product RecommendationRecommendation SystemsSession-Based Recommendations

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Product Recommendation Coveo Data Challenge Dataset Ensemble (60 models) F1 0.0748 #1 of 1 Archive leaderboard report
Product Recommendation Coveo Data Challenge Dataset Ensemble (60 models) MRR 0.2784 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAdaptive Input RepresentationsAdaptive SoftmaxAttentionBPECosine AnnealingDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingLinear Warmup With Linear DecayMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSentencePieceSoftmaxTransformerTransformer-XLVariational DropoutXLNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections