Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation

• URL: http://arxiv.org/abs/2606.06225v1
• Date: Thu, 04 Jun 2026 14:35:57 GMT
• Title: Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation
• Abstract summary: Collaborative filtering and graph-based recommendation models are highly effective because they leverage observed user interactions.<n>This challenge is further constrained by the serving interface: new content must be assigned a standalone embedding immediately.<n>We address this setting by formulating cold-start recommendation as an inductive graph-completion problem on a temporal bipartite device-content graph.
• Score: 4.3999633581692175
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Collaborative filtering and graph-based recommendation models are highly effective because they leverage observed user interactions, but this dependence creates a fundamental cold-start challenge when newly added content has no interaction history. In Tubi's production retrieval system, this challenge is further constrained by the serving interface: new content must be assigned a standalone embedding immediately, and the model must also produce device embeddings suitable for approximate nearest-neighbor retrieval. We address this setting by formulating cold-start recommendation as an inductive graph-completion problem on a temporal bipartite device-content graph. We propose Shallow-RHS, an asymmetric link-prediction architecture in which the left-hand side (LHS) device tower leverages temporally valid watch-history message passing to capture collaborative signals, while the right-hand side (RHS) content tower is intentionally shallow with respect to the graph and encodes content solely from intrinsic features. The RHS tower does not use ID-based embeddings, content-side subgraphs, neighbor aggregation, or interaction-derived representations, forcing the content encoder to map intrinsic features into a collaborative-filtering-aware embedding space. After training, the learned content encoder generates embeddings for both warm and newly ingested content, enabling implicit graph completion through retrieval of warm surrogate neighbors. We further extend the same representation-completion principle to device cold-start by constructing cohort-based embeddings from demographic features. Large-scale online experiments demonstrate consistent relative improvements in content cold-start engagement, promotion speed, impression acquisition, and device cold-start engagement.

Related papers

• Compositional Video Generation via Inference-Time Guidance [69.53614395025632]
  Text-to-video diffusion models often fail on prompts requiring compositional understanding.<n>We propose textbfCVG, an inference-time guidance method for improving compositional faithfulness in frozen text-to-video models.
  arXiv  Detail & Related papers  (2026-05-14T15:50:25Z)
• Triple Spectral Fusion for Sensor-based Human Activity Recognition [86.21994396715074]
  This paper proposes a novel triple spectral fusion framework tailored for sensor-based human activity recognition (HAR)<n>We develop an adaptive complementary filtering technique for noise suppression and organize each IMU's sensors into posture and motion modality nodes.<n>An adaptive wavelet frequency selection approach is implemented to suppress context redundancy and shorten the length of features.
  arXiv  Detail & Related papers  (2026-05-04T15:42:58Z)
• Vectorized Context-Aware Embeddings for GAT-Based Collaborative Filtering [0.0]
  This paper presents a Graph Attention Network (GAT) based Collaborative Filtering framework enhanced with Large Language Model (LLM) driven context aware embeddings.<n>Experiments on the MovieLens 100k and 1M datasets show consistent improvements over state-of-the-art baselines in Precision, NDCG, and MAP.<n>Our approach effectively mitigates sparsity and cold-start limitations by integrating LLM-derived contextual understanding into graph-based architectures.
  arXiv  Detail & Related papers  (2025-10-30T13:07:39Z)
• A Transformer Based Handwriting Recognition System Jointly Using Online and Offline Features [8.419663258260671]
  We introduce an end-to-end network that performs early fusion of offline images and online stroke data.<n>Our approach achieves state-of-the-art accuracy, exceeding previous bests by up to 1%.
  arXiv  Detail & Related papers  (2025-06-25T08:58:47Z)
• Firzen: Firing Strict Cold-Start Items with Frozen Heterogeneous and Homogeneous Graphs for Recommendation [34.414081170244955]
  We propose a unified framework incorporating multi-modal content of items and knowledge graphs (KGs) to solve both strict cold-start and warm-start recommendation. Our model yields significant improvements for strict cold-start recommendation and outperforms or matches the state-of-the-art performance in the warm-start scenario.
  arXiv  Detail & Related papers  (2024-10-10T06:48:27Z)
• Asynchronous Graph Generator [0.0]
  AGG encodes measurements, timestamps and channel-specific features directly in the nodes via learnable embeddings.<n>AGG performs imputation by emphconditional attention generation, i.e., by creating a new node conditioned on given timestamps and channel specification.<n>Our experiments reveal that AGG achieved state-of-the-art results in time series imputation, classification and prediction for the benchmark datasets emphBeijing Air Quality, emphPhysioNet ICU 2012 and emphUCI localisation, outperforming other recent attention
  arXiv  Detail & Related papers  (2023-09-29T15:46:41Z)
• A Graph-Enhanced Click Model for Web Search [67.27218481132185]
  We propose a novel graph-enhanced click model (GraphCM) for web search. We exploit both intra-session and inter-session information for the sparsity and cold-start problems.
  arXiv  Detail & Related papers  (2022-06-17T08:32:43Z)
• Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation [62.96628432641806]
  Scene Graph Generation aims to first encode the visual contents within the given image and then parse them into a compact summary graph. We first present a novel Stacked Hybrid-Attention network, which facilitates the intra-modal refinement as well as the inter-modal interaction. We then devise an innovative Group Collaborative Learning strategy to optimize the decoder.
  arXiv  Detail & Related papers  (2022-03-18T09:14:13Z)
• Learning Expanding Graphs for Signal Interpolation [14.84852576248587]
  We propose an attachment model for incoming nodes parameterized by the probabilities and connectivity of the specific node. We study real data dealing in cold start collaborative recommendations.
  arXiv  Detail & Related papers  (2022-03-15T14:51:29Z)
• Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer [69.0621959845251]
  We propose a new framework Temporal Graph Sequential Recommender (TGSRec) upon our defined continuous-time bi-partite graph. TCT layer can simultaneously capture collaborative signals from both users and items, as well as considering temporal dynamics inside sequential patterns. Empirical results on five datasets show that TGSRec significantly outperforms other baselines.
  arXiv  Detail & Related papers  (2021-08-14T22:50:53Z)
• Privileged Graph Distillation for Cold Start Recommendation [57.918041397089254]
  The cold start problem in recommender systems requires recommending to new users (items) based on attributes without any historical interaction records. We propose a privileged graph distillation model(PGD) Our proposed model is generally applicable to different cold start scenarios with new user, new item, or new user-new item.
  arXiv  Detail & Related papers  (2021-05-31T14:05:27Z)
• Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph [54.03786611989613]
  signed link prediction in social networks aims to reveal the underlying relationships (i.e. links) among users (i.e. nodes) We develop a unified framework, termed as Signed Infomax Hyperbolic Graph (textbfSIHG) In order to model high-order user relations and complex hierarchies, the node embeddings are projected and measured in a hyperbolic space with a lower distortion.
  arXiv  Detail & Related papers  (2020-11-25T05:09:03Z)

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.