Hansheng Ren

Hansheng Ren

Current paradigms in Deep Learning prioritize computational throughput over numerical precision, relying on the assumption that intelligence emerges from statistical correlation at scale. In this paper, we challenge this orthodoxy. We propose the Exactness Hypothesis: that General Intelligence (AGI), specifically high-order causal inference, requires a computational substrate capable of Arbitrary Precision Arithmetic. We argue that the "hallucinations" and logical incoherence seen in current Large Language Models (LLMs) are artifacts of IEEE 754 floating-point approximation errors accumulating over deep compositional functions. To mitigate this, we introduce the Halo Architecture, a paradigm shift to Rational Arithmetic ($\mathbb{Q}$) supported by a novel Exact Inference Unit (EIU). Empirical validation on the Huginn-0125 prototype demonstrates that while 600B-parameter scale BF16 baselines collapse in chaotic systems, Halo maintains zero numerical divergence indefinitely. This work establishes exact arithmetic as a prerequisite for reducing logical uncertainty in System 2 AGI.

Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang et al.

Despite the wide application of Graph Convolutional Network (GCN), one major limitation is that it does not benefit from the increasing depth and suffers from the oversmoothing problem. In this work, we first characterize this phenomenon from the information-theoretic perspective and show that under certain conditions, the mutual information between the output after $l$ layers and the input of GCN converges to 0 exponentially with respect to $l$. We also show that, on the other hand, graph decomposition can potentially weaken the condition of such convergence rate, which enabled our analysis for GraphCNN. While different graph structures can only benefit from the corresponding decomposition, in practice, we propose an automatic connectivity-aware graph decomposition algorithm, DeGNN, to improve the performance of general graph neural networks. Extensive experiments on widely adopted benchmark datasets demonstrate that DeGNN can not only significantly boost the performance of corresponding GNNs, but also achieves the state-of-the-art performances.

Hansheng Ren, Bixiong Xu, Yujing Wang et al.

Large companies need to monitor various metrics (for example, Page Views and Revenue) of their applications and services in real time. At Microsoft, we develop a time-series anomaly detection service which helps customers to monitor the time-series continuously and alert for potential incidents on time. In this paper, we introduce the pipeline and algorithm of our anomaly detection service, which is designed to be accurate, efficient and general. The pipeline consists of three major modules, including data ingestion, experimentation platform and online compute. To tackle the problem of time-series anomaly detection, we propose a novel algorithm based on Spectral Residual (SR) and Convolutional Neural Network (CNN). Our work is the first attempt to borrow the SR model from visual saliency detection domain to time-series anomaly detection. Moreover, we innovatively combine SR and CNN together to improve the performance of SR model. Our approach achieves superior experimental results compared with state-of-the-art baselines on both public datasets and Microsoft production data.