ACE: Semantically-Grounded Graph Alignment via Affective Contrastive Learning
sigir26-002 · Full research paper · Potito Aghilar, Sabino Roccotelli, Vito Walter Anelli, Alejandro Bellogín, Michelantonio Trizio, Tommaso Di Noia
Graph Contrastive and Self-Supervise · 50% Graph Contrastive and Self-Supervise · 50%
Abstract
Graph Contrastive Learning (GCL) methods for recommendation learn representations by propagating signals over user-item interaction graphs. However, modeling these graphs with homogeneous edges can lead to semantic-structural misalignment, where information is exchanged between structurally adjacent but semantically dissimilar items, adversely affecting retrieval quality. Existing solutions typically rely on auxiliary encoders or additional supervision, increasing model complexity and training cost. We propose ACE (Affective Contrastive Embeddings), a framework that improves representation alignment by incorporating affective semantics into contrastive learning. ACE encodes the affective dimensions of valence and arousal as a topological prior, encouraging consistency between learned embeddings and an affective semantic space distilled from large language models. To operationalize this alignment, we introduce a Semantically Weighted Noise Contrastive Estimation (SW-NCE) loss that modulates contrastive gradients according to users' affective preferences. Experiments on Amazon, Last.fm, and SiTunes demonstrate that ACE consistently improves top-K retrieval performance over 11 baselines while reducing computational overhead. These results indicate that affective geometric alignment is an effective and efficient mechanism for enhancing graph-based retrieval models.
Assigned reviewers
| # | Reviewer | Match | Why (closest evidence publications in the taxonomy) | |
|---|---|---|---|---|
| 1 | Lianghao Xia | 65 | 100 LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning 100 Automated Self-Supervised Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning 85 Self-Supervised Hypergraph Transformer for Recommender Systems (2022) Graph Contrastive and Self-Supervised Learning |
|
| 2 | Yinwei Wei | 62 | 88 MultiCBR: Multi-view Contrastive Learning for Bundle Recommendation (2024) Graph Contrastive and Self-Supervised Learning 84 Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation (2025) Graph Contrastive and Self-Supervised Learning 84 Multi-modal Bipartite Graph Structure Learning with Information Bottleneck for Micro-video Recommendation (2026) Graph Contrastive and Self-Supervised Learning |
|
| 3 | Mengyuan Jing | 62 | 76 Graph Contrastive Learning with Adaptive Augmentation for Recommendation (2022) Graph Contrastive and Self-Supervised Learning 76 Review-Enhanced Hierarchical Contrastive Learning for Recommendation (2024) Graph Contrastive and Self-Supervised Learning 76 Rating-Review Graph Contrastive Learning for Review-based Recommendation (2023) Graph Contrastive and Self-Supervised Learning |
Area chair
| Area chair | Match | |
|---|---|---|
| Leyu Lin | 45 |
Area-chair candidates (4)
| Leyu Lin assigned | 45 | 15 papers | |
| Qiaoyu Tan | 44 | 7 papers | |
| Weiming Liu 0005 | 43 | 8 papers | |
| Kun Gai | 40 | 5 papers |
Candidates from the panel ranked by match score
| # | Reviewer | Match | Load | Why | |
|---|---|---|---|---|---|
| 1 | Lianghao Xia assigned | 65 | 3 | 100 LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning 100 Automated Self-Supervised Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning |
|
| 2 | Yinwei Wei assigned | 62 | 3 | 88 MultiCBR: Multi-view Contrastive Learning for Bundle Recommendation (2024) Graph Contrastive and Self-Supervised Learning 84 Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation (2025) Graph Contrastive and Self-Supervised Learning |
|
| 3 | Mengyuan Jing assigned | 62 | 3 | 76 Graph Contrastive Learning with Adaptive Augmentation for Recommendation (2022) Graph Contrastive and Self-Supervised Learning 76 Review-Enhanced Hierarchical Contrastive Learning for Recommendation (2024) Graph Contrastive and Self-Supervised Learning |
|
| 4 | Ke Wang 0038 | 62 | 3 | 84 Review-Enhanced Hierarchical Contrastive Learning for Recommendation (2024) Graph Contrastive and Self-Supervised Learning 84 Multi-aspect Graph Contrastive Learning for Review-enhanced Recommendation (2024) Graph Contrastive and Self-Supervised Learning |
|
| 5 | Yi Zhang 0103 | 56 | 3 | 100 Unveiling Contrastive Learning's Capability of Neighborhood Aggregation for Collaborative Filtering (2025) Graph Contrastive and Self-Supervised Learning 100 MixRec: Individual and Collective Mixing Empowers Data Augmentation for Recommender Systems (2025) Graph Contrastive and Self-Supervised Learning |
|
| 6 | Xubin Ren | 56 | 3 | 76 Disentangled Contrastive Collaborative Filtering (2023) Graph Contrastive and Self-Supervised Learning 76 LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning |
|
| 7 | Dongxiao He | 55 | 3 | 76 A New Mechanism for Eliminating Implicit Conflict in Graph Contrastive Learning (2024) Graph Contrastive and Self-Supervised Learning 76 Contrastive Learning Meets Homophily: Two Birds with One Stone (2023) Graph Contrastive and Self-Supervised Learning |
|
| 8 | Wei Wei 0027 | 53 | 3 | 85 Heterogeneous Graph Contrastive Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning 69 Multi-Relational Contrastive Learning for Recommendation (2023) Graph Contrastive and Self-Supervised Learning |
|
| 9 | Jiuqiang Li 0002 | 53 | 3 | 62 Graph Diffusive Self-Supervised Learning for Social Recommendation (2024) Social and Group Recommendation 47 Disentangled Contrastive Bundle Recommendation with Conditional Diffusion (2025) Diffusion and Flow Recommenders |
|
| 10 | Chunyang Wang 0001 | 51 | 3 | 84 Guiding Graph Learning with Denoised Modality for Multi-modal Recommendation (2024) Graph Contrastive and Self-Supervised Learning 84 Review-Enhanced Hierarchical Contrastive Learning for Recommendation (2024) Graph Contrastive and Self-Supervised Learning |
|
| 11 | Yongjing Hao | 47 | 3 | 85 LMACL: Improving Graph Collaborative Filtering with Learnable Model Augmentation Contrastive Learning (2024) Graph Contrastive and Self-Supervised Learning 85 Meta-optimized Structural and Semantic Contrastive Learning for Graph Collaborative Filtering (2024) Graph Contrastive and Self-Supervised Learning |
|
| 12 | Xiaolong Liu 0012 | 47 | 3 | 77 Graph-based Alignment and Uniformity for Recommendation (2023) Graph-based User and Item Representation Learning 69 Collaborative Alignment for Recommendation (2024) Graph Contrastive and Self-Supervised Learning |
|
| 13 | Lantao Hu | 47 | 3 | 76 Towards Robust Recommendation via Decision Boundary-aware Graph Contrastive Learning (2024) Graph Contrastive and Self-Supervised Learning 75 Soft Contrastive Sequential Recommendation (2024) Contrastive and Self-Supervised Sequential Recommendation |
|
| 14 | Bowen Zheng 0005 | 46 | 3 | 100 Enhancing Graph Contrastive Learning with Reliable and Informative Augmentation for Recommendation (2025) Graph Contrastive and Self-Supervised Learning 44 Generative Recommender with End-to-End Learnable Item Tokenization (2025) Item Tokenization and Semantic IDs |
|
| 15 | Yixin Liu 0001 | 46 | 3 | 76 Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating (2023) Graph Contrastive and Self-Supervised Learning 76 Learning Strong Graph Neural Networks with Weak Information (2023) Graph Contrastive and Self-Supervised Learning |
|
| 16 | Chen Wang 0052 | 46 | 3 | 77 Graph-based Alignment and Uniformity for Recommendation (2023) Graph-based User and Item Representation Learning 51 Group Identification via Transitional Hypergraph Convolution with Cross-view Self-supervised Learning (2023) Social and Group Recommendation |
|
| 18 | Jiancan Wu | 45 | 3 | 100 Self-supervised Graph Learning for Recommendation (2021) Graph Contrastive and Self-Supervised Learning 85 Graph Contrastive Learning With Negative Propagation for Recommendation (2024) Graph Contrastive and Self-Supervised Learning |
|
| 20 | Mingdai Yang | 44 | 3 | 77 Graph-based Alignment and Uniformity for Recommendation (2023) Graph-based User and Item Representation Learning 66 Collaborative Alignment for Recommendation (2024) Graph Contrastive and Self-Supervised Learning |
|
| 21 | Yong He 0009 | 44 | 3 | 76 Global-Aware Model-Free Self-distillation for Recommendation System (2023) Graph Contrastive and Self-Supervised Learning 47 The Devil is in the Sources! Knowledge Enhanced Cross-Domain Recommendation in an Information Bottleneck Perspective (2024) Domain Adaptation and Disentangled Representation for CDR |
|
| 22 | Lingling Yi | 43 | 3 | 75 Dual Interests-Aligned Graph Auto-Encoders for Cross-domain Recommendation in WeChat (2023) Graph Contrastive and Self-Supervised Learning 71 Item-Provider Co-learning for Sequential Recommendation (2022) Graph Contrastive and Self-Supervised Learning |
|
| 24 | Min Hou 0004 | 43 | 3 | 66 Unified Representation Learning for Discrete Attribute Enhanced Completely Cold-Start Recommendation (2025) Graph Contrastive and Self-Supervised Learning 66 Pre-training General User Representation with Multi-type APP Behaviors (2024) Recommendation Systems and Evaluation |
|
| 25 | Lichan Hong | 43 | 3 | 76 Self-supervised Learning for Large-scale Item Recommendations (2021) Graph Contrastive and Self-Supervised Learning 45 Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations (2024) Item Tokenization and Semantic IDs |
|
| 26 | Ed H. Chi | 42 | 3 | 76 Self-supervised Learning for Large-scale Item Recommendations (2021) Graph Contrastive and Self-Supervised Learning 45 Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations (2024) Item Tokenization and Semantic IDs |
|
| 27 | Jiangxia Cao | 42 | 3 | 47 DisenCDR: Learning Disentangled Representations for Cross-Domain Recommendation (2022) Domain Adaptation and Disentangled Representation for CDR 47 Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck (2022) Domain Adaptation and Disentangled Representation for CDR |
|
| 28 | Riwei Lai | 42 | 3 | 67 Disentangled Negative Sampling for Collaborative Filtering (2023) Graph Contrastive and Self-Supervised Learning 44 Multi-Faceted Global Item Relation Learning for Session-Based Recommendation (2022) Graph-Based Sequential and Session Recommendation |
|
| 29 | Hao Liu 0078 | 41 | 3 | 47 DA-DAN: A Dual Adversarial Domain Adaption Network for Unsupervised Non-overlapping Cross-domain Recommendation (2024) Domain Adaptation and Disentangled Representation for CDR 45 Mitigating Distribution Shifts in Sequential Recommendation: An Invariance Perspective (2025) Contrastive and Self-Supervised Sequential Recommendation |
|
| 30 | Jing Zhu 0005 | 41 | 3 | 59 Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning (2025) Multimodal and Cross-Modal Retrieval › Others 53 Node Proximity Is All You Need: Unified Structural and Positional Node and Graph Embedding (2021) Graph-based User and Item Representation Learning |
|
| 31 | Jieming Zhu | 41 | 3 | 45 CoST: Contrastive Quantization based Semantic Tokenization for Generative Recommendation (2024) Item Tokenization and Semantic IDs 45 UNGER: Generative Recommendation with A Unified Code via Semantic and Collaborative Integration (2026) Item Tokenization and Semantic IDs |
|
| 32 | Hao Deng 0011 | 40 | 3 | 45 MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation (2026) Item Tokenization and Semantic IDs 44 REG4Rec: Reasoning-Enhanced Generative Model for Large-Scale Recommendation Systems (2026) Item Tokenization and Semantic IDs |
|
| 34 | Wei Guo 0006 | 40 | 3 | 75 Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation (2023) Graph Contrastive and Self-Supervised Learning 42 Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model (2025) Generative Retrieval and Ranking |