Machine Learning

ADV-TRA uses adversarial trajectories to robustly fingerprint deep neural networks, outperforming state-of-the-art methods against various removal attacks.

UniIF: A unified model revolutionizes molecule inverse folding, achieving state-of-the-art results across protein, RNA, and material design by employing a novel geometric block attention network.

UniGAD unifies multi-level graph anomaly detection, improving accuracy and zero-shot transferability by jointly modeling node, edge, and graph anomalies via a novel subgraph sampler and GraphStitch Ne…

TFE-GNN: A novel spectral GNN using triple filter ensembles for superior homophily/heterophily handling and improved generalization on real-world graphs.

Latent Graph Diffusion (LGD) unifies graph learning, solving all task levels and types with a single framework and state-of-the-art results.

This paper introduces the Uniform Last-Iterate (ULI) guarantee, a novel metric for evaluating reinforcement learning algorithms that considers both cumulative and instantaneous performance. Unlike ex…

Unified Graph Augmentations (UGA) module boosts graph contrastive learning by unifying diverse augmentation strategies, improving model generalizability and efficiency.

E-SSL’s generalization ability is rigorously analyzed via an information-theoretic lens, revealing key design principles for improved performance.

Repeated self-distillation significantly reduces excess risk in linear regression, achieving up to a ’d’ factor improvement over single-step methods.

A mean-field theory explains Fourier Neural Operator (FNO) behavior, linking expressivity to trainability by identifying ordered and chaotic phases that correspond to vanishing or exploding gradients,…

Deep Equilibrium Models excel on imbalanced data due to feature convergence and self-duality properties, unlike explicit models, as shown through Neural Collapse analysis.

Larger machine learning models don’t always mean better performance; strategic interactions can reverse this trend, as this research shows, prompting a new paradigm for model selection in games.

Diffusion models’ surprising generalizability stems from an inductive bias towards learning Gaussian data structures, a finding that reshapes our understanding of their training and generalization.

Graph self-supervised learning models surprisingly exhibit high redundancy, allowing for significant parameter reduction without performance loss. A novel framework, SLIDE, leverages this discovery f…

Biologically-inspired ORGANICs neural circuit achieves dynamic divisive normalization, ensuring unconditional stability and seamless backpropagation training for high-dimensional recurrent networks.

TRACER, a novel robust offline RL algorithm, uses Bayesian inference to handle uncertainty from diverse data corruptions, significantly outperforming existing methods.

UGC: Blazing-fast graph coarsening for big data, preserving key insights across diverse graph types.

Two-way Deconfounder tackles off-policy evaluation challenges by introducing a novel two-way unmeasured confounding assumption and a neural-network-based deconfounder, achieving consistent policy valu…

TuneTables optimizes PFNs for scalability via context optimization, achieving state-of-the-art performance on large tabular datasets while using fewer parameters and reducing inference time.

Faster algorithms for solving discounted Markov Decision Processes (DMDPs) are introduced, achieving near-optimal sample and time complexities, especially in the sample setting and improving runtimes …