8 papers · 1 filter
Continual Test-Time Learning with Evolution Strategies
Guangya Hao, Yiting Duan, Longyan Tan +5
Large language models increasingly operate in open-ended environments, where they are expected to continually adapt to evolving tasks and distributions, often without access to ext…
Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training
Yunbo Long, Tejumade Afonja, Guangya Hao +2
Tabular language models can generate synthetic tables by modeling rows as token sequences, but they are typically trained once with supervised fine-tuning and then used as static s…
Topological Federated Clustering via Gravitational Potential Fields under Local Differential Privacy
Yunbo Long, Jiaquan Zhang, Xi Chen +1
Clustering non-independent and identically distributed (non-IID) data under local differential privacy (LDP) in federated settings presents a critical challenge: preserving privacy…
PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data
Yunbo Long, Liming Xu, Ge Zheng +1
Federated learning (FL) enables retailers to share model parameters for demand forecasting while maintaining privacy. However, heterogeneous data across diverse regions, driven by…
Efficient and Privacy-Preserved Link Prediction via Condensed Graphs
Yunbo Long, Liming Xu, Alexandra Brintrup
Link prediction is crucial for uncovering hidden connections within complex networks, enabling applications such as identifying potential customers and products. However, this rese…
LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion
Yunbo Long, Liming Xu, Alexandra Brintrup
Synthetic tabular data are increasingly being used to replace real data, serving as an effective solution that simultaneously protects privacy and addresses data scarcity. However,…
Evaluating Inter-Column Logical Relationships in Synthetic Tabular Data Generation
Yunbo Long, Liming Xu, Alexandra Brintrup
Current evaluations of synthetic tabular data mainly focus on how well joint distributions are modeled, often overlooking the assessment of their effectiveness in preserving realis…
Random Walk Guided Hyperbolic Graph Distillation
Yunbo Long, Liming Xu, Stefan Schoepf +1
Graph distillation (GD) is an effective approach to extract useful information from large-scale network structures. However, existing methods, which operate in Euclidean space to g…