arXiv:2602.01828v2 Announce Type: replace Abstract: Many complex networks exhibit hierarchical, tree-like structures, making hyperbolic space a natural candidate wherein to learn representations of them. Based on this observation, Hyperbolic Graph Neural Networks (HGNNs) have been widely adopted as a principled…
arXiv:2605.14067v1 Announce Type: new Abstract: Financial distress prediction remains a significant challenge in enterprise risk analysis due to the highly imbalanced nature of real-world financial datasets, where bankrupt or distressed firms typically constitute only a small minority of observations. This…
arXiv:2603.07833v2 Announce Type: replace Abstract: Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent’s long-term outcomes. Most approaches in this paradigm implement a semi-gradient update to boost the learning speed, which consists of ignoring the gradient of…
arXiv:2605.14069v1 Announce Type: new Abstract: Irregularly sampled multivariate event streams remain a stubbornly difficult modality for generative modeling: tokenization-based approaches break down when inter-event intervals vary by orders of magnitude, and neural temporal point processes are bottlenecked by window-level numerical…
arXiv:2605.02043v2 Announce Type: replace Abstract: Asynchronous stochastic gradient descent (SGD) enables scalable distributed training but suffers from gradient staleness. Existing mitigation strategies, such as delay-adaptive learning rates and staleness-aware filtering, typically attenuate or discard delayed gradients, introducing systematic bias: updates…
arXiv:2605.14073v1 Announce Type: new Abstract: Deep neural networks have achieved strong performance in genomic sequence classification; however, relating their predictions to biologically meaningful sequence patterns remains challenging. In this work, we present AttnGen, an attention-guided training framework that embeds interpretability…
arXiv:2605.10289v2 Announce Type: replace Abstract: Offline-to-online learning aims to improve online decision-making by leveraging offline logged data. A central challenge in this setting is the distribution shift between offline and online environments. While some existing works attempt to leverage shifted…
arXiv:2605.14074v1 Announce Type: new Abstract: Fairness in toxicity classification involves three integrated axes: ranking, calibration, and abstention. Training-time interventions and post-hoc safety mechanisms cannot be evaluated independently because the former determines the efficacy of the latter. We compare Empirical Risk…
arXiv:2605.12998v2 Announce Type: replace Abstract: Continual graph learning (CGL) aims to learn from dynamically evolving graphs while mitigating catastrophic forgetting. Existing CGL approaches typically adopt a task-based formulation, where the data stream is partitioned into a sequence of discrete tasks…
arXiv:2605.14075v1 Announce Type: new Abstract: Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more interpretable and optimized architectures. Mechanistic interpretability has led to the development of various methods for assessing layer…
