Establishing the robustness of chip trade networks by dynamically considering topology and risk cascading propagation

Abstract

Risk cascading propagation research mostly focuses on complex theoretical networks. Recently, the vulnerability of international chip supply has increased notably, and it is strategically important to explore how shortage risk affects the emergence dynamics of the real chip trade systems. This study abstracts the global chip trade relationship data for 2009-2021 into multiple asymmetrically weighted networks. Using macro-network and micro-node indicators, we explore the topological traits of international chip trade networks and their evolutionary laws. Accordingly, we propose risk cascading propagation models driven by node failure and edge restraint and further innovate to open up the research paradigm of focused-edge networks. Furthermore, a community infection-driven risk cascading propagation mechanism that incorporates community risk absorption capacity is introduced, considering both the propagation attenuation effects and the trade dependency degree. A multi-dimensional dynamic perspective reveals the hidden systemic risks in international chip trade. The main results are as follows: first, international chip trade networks are highly connected and cohesive, consistent with small-world characteristics. Second, the proportion of economies that collapse because of supply shortage risk shocks increases with the impact coefficient $\alpha /\beta$ . The dominant power in chip crisis propagation has shifted from Europe and America to Asia, and mainland China's risk penetration capacity has enhanced significantly. Third, focused-edge networks conform to a multi-hub radiation pattern. Before the COVID-19 pandemic, the degree of control and spillover effects of chip supply shortages in hub economies on the international trade was increasing progressively. Fourth, an increase in absorption capacity $\lambda$ or attenuation factor $\gamma$ consistently leads to a decline in avalanche scale, with $\lambda$ exhibiting critical thresholds. These findings will help policymakers pursue efficient management strategies for chip trade, thereby improving supply stability and security.

Fig. 1

Schematic diagrams of risk cascading propagation driven by node failure, edge restraint, and community infection.

Fig. 2

Total volume of international chip trade from 2009 to 2021.

Fig. 3

Network density and reciprocity of international chip trade networks from 2009 to 2021.

Fig. 4

Dynamic evolution of degree centrality and betweenness centrality in the seven core economies from 2009 to 2021.

Fig. 5

Avalanche ratios of international chip trade networks when 30 major risk sources reduce supply under different impact coefficients $\alpha /\beta$ (Study period: 2009–2021).

Fig. 6

Relationship between the proportion of export shrinkage in key economies and the avalanche ratios of international chip trade networks when fixing the infection threshold $\beta$ (Study period: 2009–2021; the legend is arranged based on the influence intensity in descending order).

Fig. 7

Risk propagation paths when mainland China is the initial risk source (Study period: 2009–2021; the sequence of node failures is color-coded as red, green, yellow, and blue).

Fig. 8

Dynamic evolution of focused-edge networks from 2009 to 2021.

Fig. 9

Study on the impact of parameters $\lambda$ and $\gamma$ in the community infection-driven risk propagation model (considering propagation attenuation). Panels (a) and (c) investigate the effects of $\lambda$ and $\gamma$ on the network avalanche scale, while Panels (b) and (d) examine community infection status when key risk sources reduce chip exports under critical $\lambda$ values (study years: 2009, 2021).

Fig. 10

Research exploring the dominant economies and risk propagation paths in the community infection-driven risk propagation model (considering trade dependency). Panels (a) and (c) depict the top ten economies by weighted degree in the chip trade dependency networks, while Panels (b) and (d) illustrate the risk propagation paths within and outside the community when mainland China is the initial risk source (study years: 2009, 2021; the sequence of node failures is color-coded as red, yellow, pink, green, and blue).