M2TRec: Metadata-aware Multi-task Transformer for Large-scale and
Cold-start free Session-based Recommendations
- URL: http://arxiv.org/abs/2209.11824v1
- Date: Fri, 23 Sep 2022 19:34:29 GMT
- Title: M2TRec: Metadata-aware Multi-task Transformer for Large-scale and
Cold-start free Session-based Recommendations
- Authors: Walid Shalaby, Sejoon Oh, Amir Afsharinejad, Srijan Kumar, Xiquan Cui
- Abstract summary: Session-based recommender systems (SBRSs) have shown superior performance over conventional methods.
We propose M2TRec, a Metadata-aware Multi-task Transformer model for session-based recommendations.
- Score: 9.327321259021236
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Session-based recommender systems (SBRSs) have shown superior performance
over conventional methods. However, they show limited scalability on
large-scale industrial datasets since most models learn one embedding per item.
This leads to a large memory requirement (of storing one vector per item) and
poor performance on sparse sessions with cold-start or unpopular items. Using
one public and one large industrial dataset, we experimentally show that
state-of-the-art SBRSs have low performance on sparse sessions with sparse
items. We propose M2TRec, a Metadata-aware Multi-task Transformer model for
session-based recommendations. Our proposed method learns a transformation
function from item metadata to embeddings, and is thus, item-ID free (i.e.,
does not need to learn one embedding per item). It integrates item metadata to
learn shared representations of diverse item attributes. During inference, new
or unpopular items will be assigned identical representations for the
attributes they share with items previously observed during training, and thus
will have similar representations with those items, enabling recommendations of
even cold-start and sparse items. Additionally, M2TRec is trained in a
multi-task setting to predict the next item in the session along with its
primary category and subcategories. Our multi-task strategy makes the model
converge faster and significantly improves the overall performance.
Experimental results show significant performance gains using our proposed
approach on sparse items on the two datasets.
Related papers
- Train Once, Deploy Anywhere: Matryoshka Representation Learning for Multimodal Recommendation [27.243116376164906]
We introduce a lightweight framework called full-scale Matryoshka representation learning for multimodal recommendation (fMRLRec)
Our fMRLRec captures item features at different granularities, learning informative representations for efficient recommendation across multiple dimensions.
We demonstrate the effectiveness and efficiency of fMRLRec on multiple benchmark datasets.
arXiv Detail & Related papers (2024-09-25T05:12:07Z) - LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation [58.04939553630209]
In real-world systems, most users interact with only a handful of items, while the majority of items are seldom consumed.
These two issues, known as the long-tail user and long-tail item challenges, often pose difficulties for existing Sequential Recommendation systems.
We propose the Large Language Models Enhancement framework for Sequential Recommendation (LLM-ESR) to address these challenges.
arXiv Detail & Related papers (2024-05-31T07:24:42Z) - MMGRec: Multimodal Generative Recommendation with Transformer Model [81.61896141495144]
MMGRec aims to introduce a generative paradigm into multimodal recommendation.
We first devise a hierarchical quantization method Graph CF-RQVAE to assign Rec-ID for each item from its multimodal information.
We then train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences.
arXiv Detail & Related papers (2024-04-25T12:11:27Z) - Ada-Retrieval: An Adaptive Multi-Round Retrieval Paradigm for Sequential
Recommendations [50.03560306423678]
We propose Ada-Retrieval, an adaptive multi-round retrieval paradigm for recommender systems.
Ada-Retrieval iteratively refines user representations to better capture potential candidates in the full item space.
arXiv Detail & Related papers (2024-01-12T15:26:40Z) - Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item
Recommendation [71.5871100348448]
ColdGPT models item-attribute correlations into an item-attribute graph by extracting fine-grained attributes from item contents.
ColdGPT transfers knowledge into the item-attribute graph from various available data sources, i.e., item contents, historical purchase sequences, and review texts of the existing items.
Extensive experiments show that ColdGPT consistently outperforms the existing SCS recommenders by large margins.
arXiv Detail & Related papers (2023-06-26T07:04:47Z) - Language-aware Multiple Datasets Detection Pretraining for DETRs [4.939595148195813]
We propose a framework for utilizing Multiple datasets to pretrain DETR-like detectors, termed METR.
It converts the typical multi-classification in object detection into binary classification by introducing a pre-trained language model.
We show METR achieves extraordinary results on either multi-task joint training or the pretrain & finetune paradigm.
arXiv Detail & Related papers (2023-04-07T10:34:04Z) - The Minority Matters: A Diversity-Promoting Collaborative Metric
Learning Algorithm [154.47590401735323]
Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems.
This paper focuses on a challenging scenario where a user has multiple categories of interests.
We propose a novel method called textitDiversity-Promoting Collaborative Metric Learning (DPCML)
arXiv Detail & Related papers (2022-09-30T08:02:18Z) - Sequential Modeling with Multiple Attributes for Watchlist
Recommendation in E-Commerce [67.6615871959902]
We study the watchlist functionality in e-commerce and introduce a novel watchlist recommendation task.
Our goal is to prioritize which watchlist items the user should pay attention to next by predicting the next items the user will click.
Our proposed recommendation model, Trans2D, is built on top of the Transformer architecture.
arXiv Detail & Related papers (2021-10-18T10:02:15Z) - Incorporating User Micro-behaviors and Item Knowledge into Multi-task
Learning for Session-based Recommendation [18.516121495514007]
Session-based recommendation (SR) aims to predict the next interacted item based on a given session.
Most existing SR models only focus on exploiting the consecutive items in a session interacted by a certain user.
We propose a novel SR model MKM-SR, which incorporates user Micro-behaviors and item Knowledge into Multi-task learning for Session-based Recommendation.
arXiv Detail & Related papers (2020-06-12T03:06:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.