21 citations · 24 across the 11 of their papers we have counts for
9 papers · 1 filter
Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated Learning
Pengfei Li, Mohammad Khalil
Federated learning faces severe communication bottlenecks when clients upload high-dimensional model updates. Existing methods often compress these updates uniformly across all lay…
PEG-Tab: Sampling-Time Record Repair and Release Control for Tabular Synthesis
Pengfei Li, QinYi Liu, Mohammad Khalil
Pretrained tabular generators can reproduce training records even when aggregate utility remains high. When retraining is unavailable or too costly, sampling and release are the re…
MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generation
Pengfei Li, Mohammad Khalil
This paper proposes MIND, a marginal-invariant neural dependency diffusion model for mixed-type tabular data. MIND does not directly learn the joint distribution in the original he…
Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores
Sam Urmian, Qinyi Liu, Mohammad Khalil
We formalize slate recommendation as a randomized score learner followed by deterministic selection. First, an appropriately scoped differential-privacy guarantee passes through se…
Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation
Pengfei Li, Mohammad Khalil
While federated learning enables collaborative modelling on decentralised data, standard methods merely fit historical observations. This purely observational approach is fundament…
Causal Pre-training Under the Fairness Lens: An Empirical Study of TabPFN
Qinyi Liu, Mohammad Khalil, Naman Goel
Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal…
Brief but Impactful: How Human Tutoring Interactions Shape Engagement in Online Learning
Conrad Borchers, Ashish Gurung, Qinyi Liu +3
Learning analytics can guide human tutors to efficiently address motivational barriers to learning that AI systems struggle to support. Students become more engaged when they recei…
Measuring the Impact of Student Gaming Behaviors on Learner Modeling
Qinyi Liu, Lin Li, Valdemar Švábenský +2
The expansion of large-scale online education platforms has made vast amounts of student interaction data available for knowledge tracing (KT). KT models estimate students' concept…
Quality Degradation Attack in Synthetic Data
Qinyi Liu, Dong Liu, Sam Urmian +2
Synthetic Data Generation (SDG) can be used to facilitate privacy-preserving data sharing. However, most existing research focuses on privacy attacks where the adversary is the rec…