18 papers
Beyond Fixed Depths and Widths: Optimizing Textual Decoding Tries in LLM-based Generative Recommendation
Jingzhe Liu, Hanbing Wang, Jiliang Tang +4
Generative recommendation (GR) is an increasingly popular paradigm in recommender systems, with a prominent line of work using LLMs as autoregressive backbones to predict the next…
FlexRec: Adapting LLM-based Recommenders for Flexible Needs via Reinforcement Learning
Yijun Pan, Weikang Qiu, Qiyao Ma +4
Modern recommender systems must adapt to dynamic, need-specific objectives for diverse recommendation scenarios, yet most traditional recommenders are optimized for a single static…
Plain Transformers are Surprisingly Powerful Link Predictors
Quang Truong, Yu Song, Donald Loveland +4
Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the s…
Threshold Differential Attention for Sink-Free, Ultra-Sparse, and Non-Dispersive Language Modeling
Xingyue Huang, Xueying Ding, Mingxuan Ju +3
Softmax attention struggles with long contexts due to structural limitations: the strict sum-to-one constraint forces attention sinks on irrelevant tokens, and probability mass dis…
Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings
Xueying Ding, Xingyue Huang, Mingxuan Ju +5
Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representatio…
Understanding Generative Recommendation with Semantic IDs from a Model-scaling View
Jingzhe Liu, Liam Collins, Jiliang Tang +3
Recent advancements in generative models have allowed the emergence of a promising paradigm for recommender systems (RS), known as Generative Recommendation (GR), which tries to un…
Sequential Data Augmentation for Generative Recommendation
Geon Lee, Bhuvesh Kumar, Clark Mingxuan Ju +4
Generative recommendation plays a crucial role in personalized systems, predicting users' future interactions from their historical behavior sequences. A critical yet underexplored…
A Pre-training Framework for Relational Data with Information-theoretic Principles
Quang Truong, Zhikai Chen, Mingxuan Ju +3
Relational databases underpin critical infrastructure across a wide range of domains, yet the design of generalizable pre-training strategies for learning from relational databases…
Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
Ngoc Bui, Menglin Yang, Runjin Chen +5
Backward compatible representation learning enables updated models to integrate seamlessly with existing ones, avoiding to reprocess stored data. Despite recent advances, existing…
On the Role of Weight Decay in Collaborative Filtering: A Popularity Perspective
Donald Loveland, Mingxuan Ju, Tong Zhao +2
Collaborative filtering (CF) enables large-scale recommendation systems by encoding information from historical user-item interactions into dense ID-embedding tables. However, as e…
Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction
Zongyue Qin, Shichang Zhang, Mingxuan Ju +3
Link prediction is a crucial graph-learning task with applications including citation prediction and product recommendation. Distilling Graph Neural Networks (GNNs) teachers into M…
Beyond Unimodal Boundaries: Generative Recommendation with Multimodal Semantics
Jing Zhu, Mingxuan Ju, Yozen Liu +3
Generative recommendation (GR) has become a powerful paradigm in recommendation systems that implicitly links modality and semantics to item representation, in contrast to previous…
Enhancing Item Tokenization for Generative Recommendation through Self-Improvement
Runjin Chen, Mingxuan Ju, Ngoc Bui +7
Generative recommendation systems, driven by large language models (LLMs), present an innovative approach to predicting user preferences by modeling items as token sequences and ge…
GraphHash: Graph Clustering Enables Parameter Efficiency in Recommender Systems
Xinyi Wu, Donald Loveland, Runjin Chen +7
Deep recommender systems rely heavily on large embedding tables to handle high-cardinality categorical features such as user/item identifiers, and face significant memory constrain…
One Model for One Graph: A New Perspective for Pretraining with Cross-domain Graphs
Jingzhe Liu, Haitao Mao, Zhikai Chen +6
Graph Neural Networks (GNNs) have emerged as a powerful tool to capture intricate network patterns, achieving success across different domains. However, existing GNNs require caref…
Breaking Information Cocoons: A Hyperbolic Framework for Balancing Exploration and Exploitation in Recommender Systems
Qiyao Ma, Menglin Yang, Mingxuan Ju +3
Modern recommender systems often create information cocoons, restricting users' exposure to diverse content. The central challenge is to balance content exploration and exploitatio…
Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rank
Donald Loveland, Xinyi Wu, Tong Zhao +3
Collaborative Filtering (CF) methods dominate real-world recommender systems given their ability to learn high-quality, sparse ID-embedding tables that effectively capture user pre…
Robust Training Objectives Improve Embedding-based Retrieval in Industrial Recommendation Systems
Matthew Kolodner, Mingxuan Ju, Zihao Fan +5
Improving recommendation systems (RS) can greatly enhance the user experience across many domains, such as social media. Many RS utilize embedding-based retrieval (EBR) approaches…