ZhenChun Xu, Yi Cai, Dajun Zheng, li Yuan, Mengchen Zhao, Qixiang Wang, Jiexin Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Convolutional neural network (CNN) accelerators are widely used in artificial intelligence applications, such as image recognitions, due to their superior computing performance. However, as manufacturing technology scales down, the shrinking of chip size and the increasing of integration density make CNN accelerators vulnerable to soft errors, which are key factors affecting the reliability of integrated circuits. For emerging CNN applications where reliability is critical (such as self-driving cars), visible faults in applications’ outputs caused by soft errors may lead to catastrophic consequences. Therefore, it is important to consider reliability into CNN accelerators’ architecture design. Recent modeling and fault injection approaches analyze the reliability features of CNN models, but none evaluate the soft error reliability of CNN accelerators from architecture level. The Architectural Vulnerability Factor (AVF) indicates the probability that a soft error results in faulty computation outcomes. The Architecturally Correct Execution (ACE) method analyzes AVF of structures by identifying ACE bits and calculating their residency time. Based on the traditional ACE-based AVF analysis model, we propose a quantitative approach saca-AVF to analyze the AVF of systolic array based CNN accelerators that perform homogeneous matrix arithmetic operations instead of various kinds of instructions. We explore the reliability features of CNN accelerators under different design choices at different levels leveraging saca-AVF. We also observe several reliability characteristics of CNN accelerator architecture. We believe our proposed saca-AVF and the observations we made are able to guide designers to discover the reliability hotspots of CNN accelerators and build highly reliable CNN accelerators.

The goal of network representation learning is to embed nodes so as to encode the proximity structures of a graph into a continuous low-dimensional feature space. In this paper, we propose a novel algorithm called node2hash based on feature hashing for generating node embeddings. This approach follows the encoder-decoder framework. There are two main mapping functions in this framework. The first is an encoder to map each node into high-dimensional vectors. The second is a decoder to hash these vectors into a lower dimensional feature space. More specifically, we firstly derive a proximity measurement called expected distance as target which combines position distribution and co-occurrence statistics of nodes over random walks so as to build a proximity matrix, then introduce a set of T different hash functions into feature hashing to generate uniformly distributed vector representations of nodes from the proximity matrix. Compared with the existing state-of-the-art network representation learning approaches, node2hash shows a competitive performance on multi-class node classification and link prediction tasks on three real-world networks from various domains.

The aim of influence maximization problem is to mine a small set of influential individuals in a complex network which could reach the maximum influence spread. In this paper, an efficient fitness function based on local influence is designed to estimate the influence spread. Then, we propose a discrete particle swarm optimization based algorithm to find the final set with the maximum value of the fitness function. In the proposed algorithm, discrete position and velocity are redefined and problem-specific update rules are designed. In order to accelerate the convergence, we introduce a degree-based population initialization method and a mutation learning based local search strategy. Experimental results compared with four comparison algorithms show that our proposed algorithm is able to efficiently find good-quality solutions.