Third Workshop on Generative AI for Recommender Systems and Personalization
Transforming Personalization with Generative AI
Building personalized recommender systems and search experiences is a cornerstone of the modern data mining and applied machine learning (ML) community. Modern online platforms have a confluence of data including user-item interaction graphs, user and item-associated semantics (text, visual content, etc.), and metadata. Recent advancements in generative models and semantic encoders via large language models (LLMs), visual and audio encoders have significantly impacted research in relevant domains, enabling new directions in knowledge discovery and ability of models to better incorporate semantic context.
Executive Impact: The Generative AI Revolution
Leading the charge in personalized experiences, this workshop highlights key advancements and the experts driving them.
0
Workshop Iteration
0
Total Downloads
0
Anticipated Attendees
Meet the Organizers
Narges Tabari
Applied Scientist
Amazon.com, Inc. & AWS AI Labs
Aniket Deshmukh
Applied Scientist
Databricks Inc. & AWS AI Labs
Wang-Cheng Kang
Staff Research Engineer
Google DeepMind
Julian McAuley
Professor
University of California, San Diego
James Caverlee
Professor
Texas A&M University (TAMU)
Neil Shah
Principal Scientist
Snap Inc.
George Karypis
Senior Principal Scientist
AWS AI & University of Minnesota
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
Contextual & Sequential Modeling
Explore how Generative AI enhances contextual and sequential understanding in recommender systems, improving the relevance and flow of recommendations based on evolving user interactions.
Generative Retrieval & Applications
Dive into personalized generative retrieval, recommendation, search, and novel applications, including advanced methods like transformers as search indices and sophisticated personalized product features.
Instruction-tuned RecSys & Dialogue
Understand the power of instruction-tuned recommender systems and LLM-driven personalized dialogue systems for creating more intuitive and conversational user experiences.
Personalized Content Generation
Focus on the techniques and impact of personalized text and image generation within recommendation systems, enabling dynamic and custom content delivery.
Ethics: Privacy & Fairness
Address critical ethical considerations including privacy, fairness, explainability, and transparency in LLM-driven personalized and recommender systems to ensure responsible AI development.
Efficiency & Scalability
Investigate the challenges and solutions related to the efficiency and scalability of LLM-driven personalization and recommendation systems in real-world enterprise environments.
Evaluation & Agentic Systems
Discuss effective evaluation methodologies for LLM-driven personalization and recommendation, along with the potential and challenges of agentic systems for recommendation use-cases.
Deployment Case Studies
Review real-world deployment case studies, extracting lessons learned and best practices for integrating generative AI into production recommender systems.
Enterprise Process Flow
The journey of integrating Generative AI into enterprise recommender systems, from data foundations to future insights.
Confluence of Diverse Data Sources
→
Advancements in Generative Models & Encoders
→
Rapid Academic & Industrial Adoption
→
Bridging Generative & Conventional Systems
→
Fostering Dialogue & Future Insights
| Feature | Traditional Recommender Systems | Generative AI Recommender Systems |
|---|---|---|
| Core Mechanism | Collaborative filtering, matrix factorization, rule-based, conventional ML models. | Large Language Models (LLMs), semantic encoders, generative models for content creation and reasoning. |
| Data Utilization | User-item interactions, explicit/implicit feedback, structured metadata. | Deep semantic understanding of text, visual content, audio; multi-modal data synthesis. |
| Personalization Depth | Recommendation based on similarity and past behavior. | Contextual, nuanced understanding of user intent; personalized content generation (text, images, dialogue). |
| Key Applications | Product recommendations, content filtering, search result ranking. | Conversational assistants, personalized search, generative product features, agentic systems. |
| Key Challenges | Cold-start problem, scalability with sparse data, limited semantic understanding. | Computational cost, fairness, explainability, privacy, hallucination, control over generation. |
Impact Highlight
New Directions Generative AI drives significant advancements in knowledge discovery and personalized experiences for recommender systems.Real-World Impact: Generative AI in Industry
Challenge: Traditional recommender systems struggle with nuanced semantic understanding and generating novel, personalized experiences beyond ranking.
Solution: Leverage LLMs and advanced generative models to understand complex user intent, generate personalized content (text, images), and create interactive search/recommendation assistants.
Outcome: Companies like Amazon are deploying GenAI-powered shopping assistants (e.g., Rufus), leading to richer, conversational shopping experiences. Snap Inc. is exploring personalized visual generation (e.g., Dreams) to enhance user creativity and engagement. These initiatives demonstrate significant advancements in user satisfaction and business value.
Advanced ROI Calculator
Estimate the potential impact of integrating Generative AI into your enterprise, focusing on efficiency and cost savings in personalization and recommendation workflows.
Potential Annual Savings
$0
Annual Hours Reclaimed
0
Implementation Roadmap
A phased approach to adopting Generative AI for your recommender systems, drawing lessons from past successful workshops and industry progression.
Phase 1: Foundation & Exploration (KDD '24)
Initial workshop iteration, focusing on fundamental concepts and early research. Engaged 50-100 attendees and accepted 12 papers, laying the groundwork for future advancements.
Phase 2: Advanced Concepts & Integration (KDD '25)
Second workshop iteration, exploring more advanced generative models and initial integration strategies. Attracted 100-200 attendees, featuring star speakers and a strong set of 12 accepted papers.
Phase 3: WSDM '26 - Real-world Applications & Future Vision
The current workshop iteration, building on previous successes. Focuses on real-world applications, ethical considerations, and scalability. Anticipates over 100 attendees including key stakeholders, fostering dialogue for the future of personalized AI.
Ready to Transform Your Enterprise with Generative AI?
Unlock the full potential of personalized recommender systems and search experiences. Schedule a consultation with our experts to discuss a tailored strategy for your organization.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat