6 papers
Hyena Operator for Fast Sequential Recommendation
Jiahao Liu, Lin Li, Zhiyuan Li +3
Sequential recommendation models, particularly those based on attention, achieve strong accuracy but incur quadratic complexity, making long user histories prohibitively expensive.…
Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation
Weiwei Fang, Lin Li, Kaize Shi +2
High-fidelity social simulation is pivotal for addressing complex Web societal challenges, yet it demands agents capable of authentically replicating the dynamic spectrum of human…
Concept than Document: Context Compression via AMR-based Conceptual Entropy
Kaize Shi, Xueyao Sun, Xiaohui Tao +3
Large Language Models (LLMs) face information overload when handling long contexts, particularly in Retrieval-Augmented Generation (RAG) where extensive supporting documents often…
Certified Signed Graph Unlearning
Junpeng Zhao, Lin Li, Kaixi Hu +2
Signed graphs model complex relationships through positive and negative edges, with widespread real-world applications. Given the sensitive nature of such data, selective removal m…
Signed Graph Unlearning
Zhifei Luo, Lin Li, Xiaohui Tao +1
The proliferation of signed networks in contemporary social media platforms necessitates robust privacy-preserving mechanisms. Graph unlearning, which aims to eliminate the influen…
Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
Wenhao Yang, Lin Li, Xiaohui Tao +1
The imperative of user privacy protection and regulatory compliance necessitates sensitive data removal in model training, yet this process often induces distributional shifts that…