KuaiLive is the first publicly released real-time interactive dataset for live streaming recommendation, with logs from 23,772 users and 452,621 streamers over 21 days plus timestamps, multi-type interactions, and side features.
Canonical reference
Title resolution pending
Canonical reference. 80% of citing Pith papers cite this work as background.
27
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
DTL-NS introduces hierarchical index trees and LLM inference on item-ID encodings to identify false negatives and perform multi-view hard negative sampling for improved implicit CF recommendation.
MDCNS is a multi-source negative sampling framework for sequential recommendation that uses peer and teacher models plus divergence and consensus mechanisms to improve diversity and avoid local optima.
DPAA mitigates popularity bias in GNN-based collaborative filtering by integrating adaptive embedding-aware interaction weighting stabilized from pre-trained embeddings and layer-wise amplification of higher-order neighborhoods, outperforming prior debiasing methods on real and semi-synthetic data.
PFA adds a trainable fairness adapter to frozen recommenders and uses hierarchical exposure alignment to balance inter- and intra-group provider visibility, delivering substantial fairness gains with negligible accuracy loss on three public datasets.
GRE-MC retrieves relevant subgraphs and uses a graph transformer plus sparse codebook to complete missing modalities, outperforming prior methods on recommendation benchmarks.
KnowSA_CKP uses comparative knowledge probing to selectively augment LLM prompts for items with knowledge gaps, improving recommendation accuracy and context efficiency.
ACARec attends over artist catalogs to generate CF embeddings for new tracks, more than doubling recall and NDCG versus content-only baselines in music recommendation.
JBM-Diff applies conditional graph diffusion to remove preference-irrelevant multimodal noise and false-positive/negative behaviors, then augments training data via partial-order credibility scoring.
GTC improves multi-modal recommendation by using user-conditional diffusion-based feature filtering and total correlation optimization, achieving up to 28.3% gains in NDCG@5 on benchmarks.
Agent4POI generates context-conditioned multimodal affordance representations via a four-phase LLM agent, achieving 23.2% relative gains over baselines on POI benchmarks with reduced degradation under context shifts.
MATRAG deploys four agents (user modeling, item analysis, reasoning, explanation) plus knowledge-graph retrieval and a transparency score to raise hit rate 12.7% and NDCG 15.3% while producing explanations rated helpful by 87.4% of experts.
AsarRec learns adaptive sequence augmentations via transformation matrices and Semi-Sinkhorn projection to improve robustness of self-supervised sequential recommenders under noise.
A new offline protocol to profile recommender algorithms by stability in retaining past patterns and plasticity in adapting to changes upon retraining, with preliminary results on the GoodReads dataset.
PDQUBO is a new performance-driven QUBO method for feature selection in recommender systems that incorporates counterfactual performance impacts of features and pairs, is model-agnostic, and outperforms prior quantum and some classical baselines on CTR tasks.
DCGL introduces a dual-channel architecture with multi-level contrastive learning and frequency-adaptive fusion to improve knowledge-aware recommendations, especially in sparse data settings.
DPPMG learns discrete modal-specific preferences via a dedicated GNN from multimodal user data, quantizes them into tokens, and feeds them into generators with a consistency reward to produce personalized text and images.
A new joint spatio-temporal enlargement model for micro-video popularity prediction using frame scoring for long sequences and a topology-aware memory bank for unbounded historical associations.
Fairness-induced exploration in recommenders exhibits diminishing or non-monotonic returns that vary by user interaction history, with low-history users saturating sooner.
TASTE dataset and MuQ-token aggregation enable effective use of audio features from large music models to improve content-based music recommendations over collaborative filtering alone.
Introduces STCA for linear-complexity target-to-history attention, RLB for shared user encoding across targets, and length-extrapolative training to enable end-to-end 10K sequence modeling with observed scaling-law gains and production deployment improvements.
AMEN aligns item-scene interactions via homogeneous spaces and a TSP mechanism to let all-domain movelines differentially affect CTR predictions, reporting +11.6% CTCVR lift in A/B tests.
HGN introduces feature-level and instance-level gating plus explicit item-item products to capture long- and short-term interests for improved top-N sequential recommendation on implicit feedback.
Data portability scenarios in algorithmic pluralism produce varying effects on user utility across different recommendation algorithms.
citing papers explorer
-
KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation
KuaiLive is the first publicly released real-time interactive dataset for live streaming recommendation, with logs from 23,772 users and 452,621 streamers over 21 days plus timestamps, multi-type interactions, and side features.
-
Dual-Tree LLM-Enhanced Negative Sampling for Implicit Collaborative Filtering
DTL-NS introduces hierarchical index trees and LLM inference on item-ID encodings to identify false negatives and perform multi-view hard negative sampling for improved implicit CF recommendation.
-
Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation
MDCNS is a multi-source negative sampling framework for sequential recommendation that uses peer and teacher models plus divergence and consensus mechanisms to improve diversity and avoid local optima.
-
Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering
DPAA mitigates popularity bias in GNN-based collaborative filtering by integrating adaptive embedding-aware interaction weighting stabilized from pre-trained embeddings and layer-wise amplification of higher-order neighborhoods, outperforming prior debiasing methods on real and semi-synthetic data.
-
Post-hoc Provider Fairness Adaptation via Hierarchical Exposure Alignment
PFA adds a trainable fairness adapter to frozen recommenders and uses hierarchical exposure alignment to balance inter- and intra-group provider visibility, delivering substantial fairness gains with negligible accuracy loss on three public datasets.
-
Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion
GRE-MC retrieves relevant subgraphs and uses a graph transformer plus sparse codebook to complete missing modalities, outperforming prior methods on recommendation benchmarks.
-
Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders
KnowSA_CKP uses comparative knowledge probing to selectively augment LLM prompts for items with knowledge gaps, improving recommendation accuracy and context efficiency.
-
Leveraging Artist Catalogs for Cold-Start Music Recommendation
ACARec attends over artist catalogs to generate CF embeddings for new tracks, more than doubling recall and NDCG versus content-only baselines in music recommendation.
-
Joint Behavior-guided and Modality-coherence Conditional Graph Diffusion Denoising for Multi Modal Recommendation
JBM-Diff applies conditional graph diffusion to remove preference-irrelevant multimodal noise and false-positive/negative behaviors, then augments training data via partial-order credibility scoring.
-
User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation
GTC improves multi-modal recommendation by using user-conditional diffusion-based feature filtering and total correlation optimization, achieving up to 28.3% gains in NDCG@5 on benchmarks.
-
Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation
Agent4POI generates context-conditioned multimodal affordance representations via a four-phase LLM agent, achieving 23.2% relative gains over baselines on POI benchmarks with reduced degradation under context shifts.
-
MATRAG: Multi-Agent Transparent Retrieval-Augmented Generation for Explainable Recommendations
MATRAG deploys four agents (user modeling, item analysis, reasoning, explanation) plus knowledge-graph retrieval and a transparency score to raise hit rate 12.7% and NDCG 15.3% while producing explanations rated helpful by 87.4% of experts.
-
AsarRec: Adaptive Sequential Augmentation for Robust Self-supervised Sequential Recommendation
AsarRec learns adaptive sequence augmentations via transformation matrices and Semi-Sinkhorn projection to improve robustness of self-supervised sequential recommenders under noise.
-
Measuring the stability and plasticity of recommender systems
A new offline protocol to profile recommender algorithms by stability in retaining past patterns and plasticity in adapting to changes upon retraining, with preliminary results on the GoodReads dataset.
-
Performance-Driven QUBO for Recommender Systems on Quantum Annealers
PDQUBO is a new performance-driven QUBO method for feature selection in recommender systems that incorporates counterfactual performance impacts of features and pairs, is model-agnostic, and outperforms prior quantum and some classical baselines on CTR tasks.
-
DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation
DCGL introduces a dual-channel architecture with multi-level contrastive learning and frequency-adaptive fusion to improve knowledge-aware recommendations, especially in sparse data settings.
-
Discrete Preference Learning for Personalized Multimodal Generation
DPPMG learns discrete modal-specific preferences via a dedicated GNN from multimodal user data, quantizes them into tokens, and feeds them into generators with a consistency reward to produce personalized text and images.
-
Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction
A new joint spatio-temporal enlargement model for micro-video popularity prediction using frame scoring for long sequences and a topology-aware memory bank for unbounded historical associations.
-
Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty
Fairness-induced exploration in recommenders exhibits diminishing or non-monotonic returns that vary by user interaction history, with low-history users saturating sooner.
-
Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models
TASTE dataset and MuQ-token aggregation enable effective use of audio features from large music models to improve content-based music recommendations over collaborative filtering alone.
-
Make It Long, Keep It Fast: End-to-End 10K Long User Behavior Sequence Modeling for Billion-Scale Douyin Recommendation
Introduces STCA for linear-complexity target-to-history attention, RLB for shared user encoding across targets, and length-extrapolative training to enable end-to-end 10K sequence modeling with observed scaling-law gains and production deployment improvements.
-
All-domain Moveline Evolution Network for Click-Through Rate Prediction
AMEN aligns item-scene interactions via homogeneous spaces and a TSP mechanism to let all-domain movelines differentially affect CTR predictions, reporting +11.6% CTCVR lift in A/B tests.
-
Hierarchical Gating Networks for Sequential Recommendation
HGN introduces feature-level and instance-level gating plus explicit item-item products to capture long- and short-term interests for improved top-N sequential recommendation on implicit feedback.
-
Multistakeholder Impacts of Profile Portability in a Recommender Ecosystem
Data portability scenarios in algorithmic pluralism produce varying effects on user utility across different recommendation algorithms.
-
Beyond Isolated Clients: Integrating Graph-Based Embeddings into Event Sequence Models
Three strategies for adding graph embeddings to event sequence SSL models improve AUC by up to 2.3% on four financial and e-commerce datasets, with graph density determining the best integration approach.
-
Neural Cross-Domain Collaborative Filtering with Shared Entities
NeuCDCF is a wide-and-deep neural architecture for cross-domain collaborative filtering that jointly learns matrix factorization and deep representations, reporting better performance than prior CDCF models on four real-world datasets.
-
Effects of Foraging in Personalized Content-based Image Recommendation
Applies Information Foraging Theory to demonstrate that visual bookmarks increase the scent of recommended images in a content-based image recommender evaluated on Pinterest.