EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens
July 01, 2025 Β· Declared Dead Β· π Knowledge Discovery and Data Mining
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Chaoqun Yang, Xinyu Lin, Wenjie Wang, Yongqi Li, Teng Sun, Xianjing Han, Tat-Seng Chua
arXiv ID
2507.00715
Category
cs.IR: Information Retrieval
Citations
5
Venue
Knowledge Discovery and Data Mining
Last Checked
4 months ago
Abstract
Large Language Model-based generative recommendation (LLMRec) has achieved notable success, but it suffers from high inference latency due to massive computational overhead and memory pressure of KV Cache. Existing KV Cache reduction methods face critical limitations: cache compression offers marginal acceleration given recommendation tasks' short decoding steps, while prompt compression risks discarding vital interaction history. Through systematic analysis of attention patterns in LLMRec, we uncover two pivotal insights: 1) layer-wise attention sparsity inversion where early layers retain dense informative patterns while later layers exhibit high redundancy, and 2) dual attention sinks phenomenon where attention scores concentrate on both head and tail tokens of input sequences. Motivated by these insights, we propose EARN, an efficient inference framework that leverages the early layers to compress information into register tokens placed at the input sequence boundaries, then focuses solely on these tokens in the subsequent layers. Extensive experiments on three datasets, two LLMRec methods and two LLM architectures demonstrate EARN's superiority, achieving up to 3.79x speedup and 80.8% KV Cache reduction with better accuracy than the general finetuning approach. Our work bridges the efficiency-effectiveness gap in LLMRec, offering practical deployment advantages for industrial scenarios.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Information Retrieval
R.I.P.
π»
Ghosted
π
π
Old Age
Neural Graph Collaborative Filtering
R.I.P.
π»
Ghosted
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
R.I.P.
π»
Ghosted
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
R.I.P.
π
404 Not Found
Graph Neural Networks for Social Recommendation
R.I.P.
π»
Ghosted
Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted