eCom @ SIGIR 2023

8 papers

Top Research Directions

The 22 research directions with eCom @ SIGIR 2023 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Mitigating the Cold Start Problem in Recommender Systems225.0%
2Transparent Reasoning for Personalized Recommendation225.0%
3Advanced Representations and Denoising for Robust Recommendation112.5%
4Beyond Binary Relevance in Information Retrieval112.5%
5Bridging the Multilingual Support Gap in Specialized Systems112.5%
6Contrastive Alignment of Multi-Domain Entity Representations112.5%
7Cross Domain Recommendation Beyond Overlapping Users112.5%
8Distilling Cross-Encoders into Dual-Encoders for Efficient Retrieval112.5%
9Diversified Decoding in Autoregressive Sequence Generation112.5%
10Grounding Textual Semantics in User Behavior Logs112.5%
11Integrating Sparse and Dense Representations for Text Retrieval112.5%
12Many-to-Many Scaling for Cross-Domain Recommendation112.5%
13Mapping Semantic Descriptors to Audio Processing Parameters112.5%
14Mitigating Popularity Bias in Recommender Systems112.5%
15Neural Retrieval in Low-Resource Specialized Domains112.5%
16Pre-Training Language Models on Specialized Corpora112.5%
17Scaling Graph Neural Networks to Massive Datasets112.5%
18Semantic Resolution Limits of Pre-trained Embedding Spaces112.5%
19The Semantic Bottleneck of ID-Based Recommendation112.5%
20The Synthetic to Natural Language Generalization Gap112.5%
21Two-Stage Retrieval and Re-Ranking Pipelines112.5%
22Zero-Shot Domain Adaptation via Modular Memory Swapping112.5%

Download all directions as CSV

Institutions

Institutions credited by eCom @ SIGIR 2023 papers: a paper credits every institution named in its affiliations, once. 12 institutions share 8 credited papers.

#InstitutionPapersShare
1Amazon (United States) 225.0%
2Adobe Systems (United States) 112.5%
3Ant Group (China) 112.5%
4eBay (United States) 112.5%
5Etsy (United States) 112.5%
6Google (United States) 112.5%
7Google DeepMind (United Kingdom) 112.5%
8NEC (Japan) 112.5%
9Tsinghua University 112.5%
10Tsinghua–Berkeley Shenzhen Institute 112.5%
11University of California, Irvine 112.5%
12University of Michigan 112.5%

Download all institutions as CSV

About this data

Papers. eCom @ SIGIR 2023 lists 8 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 8 of 8 papers (100.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-22 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “eCom @ SIGIR 2023”, https://lacuna.tiptreesystems.com/venue/ecom-sigir-zs9x/2023.

Top Authors

AuthorPapers
Ido Ben-Shaul1
Jiri Gesi1
Kai Zhang1
Kai Zhong1
Masafumi Oyamada1
Michael Bendersky1
Qingjun Cui1
Sanat Sharma1
Tian Wang1
Tracy Holloway King1
Wai Kin Victor Chan1
Xinyu Hong1
Yao Yao1
Yubin Kim1

Impactful Papers

Papers from eCom @ SIGIR 2023 that shaped research clusters.

Influential

Papers

Title
Behavior-driven Query Similarity Prediction based on Pre-trained Language Models for E-Commerce Search
CDR-Adapter: Learning Adapters to Dig Out More Transferring Ability for Cross-Domain Recommendation Models
Contextual Font Recommendations Based on User Intent
Cross-Domain User Similarity without Overlapping Attributes via Optimal Transport Theory
Exploring the Viability of Synthetic Query Generation for Relevance Prediction
GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation
Pricing the Nearly Known - When Semantic Similarity is Just not Enough
XWalk: Random Walk Based Candidate Retrieval for Product Search