Optimal Short Video Ordering and Transmission Scheduling for Reducing Video Delivery Cost in Peer-to-Peer CDNs

The explosive growth of short video platforms has generated a massive surge in global traffic, imposing heavy financial burdens on content providers. While Peer-to-Peer Content Delivery Networks (PCDNs) offer a cost-effective alternative by leveraging resource-constrained edge nodes, the limited storage and concurrent service capacities of these peers struggle to absorb the intense temporal demand spikes characteristic of short video consumption. In this paper, we propose to minimize transmission costs by exploiting a novel degree of freedom, the inherent flexibility of server-driven playback sequences. We formulate the Optimal Video Ordering and Transmission Scheduling (OVOTS) problem as an Integer Linear Program to jointly optimize personalized video ordering and transmission scheduling. By strategically permuting playlists, our approach proactively smooths temporal traffic peaks, maximizing the offloading of requests to low-cost peer nodes. To solve the OVOTS problem, we provide a rigorous theoretical reduction of the OVOTS problem to an auxiliary Minimum Cost Maximum Flow (MCMF) formulation. Leveraging König's Edge Coloring Theorem, we prove the strict equivalence of these formulations and develop the Minimum-cost Maximum-flow with Edge Coloring (MMEC) algorithm, a globally optimal, polynomial-time solution. Extensive simulations demonstrate that MMEC significantly outperforms baseline strategies, achieving cost reductions of up to 67% compared to random scheduling and 36% compared to a simulated annealing approach. Our results establish playback sequence flexibility as a robust and highly effective paradigm for cost optimization in PCDN architectures.

Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability

Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases can potentially contribute to harmful real-world consequences, reinforcing stereotypes and exacerbating inequalities in various social contexts. While existing research on diffusion bias mitigation has predominantly focused on guiding content generation, it often neglects the intrinsic mechanisms within diffusion models that causally drive biased outputs. In this paper, we investigate the internal processes of diffusion models, identifying specific decision-making mechanisms, termed bias features, embedded within the model architecture. By directly manipulating these features, our method precisely isolates and adjusts the elements responsible for bias generation, permitting granular control over the bias levels in the generated content. Through experiments on both unconditional and conditional diffusion models across various social bias attributes, we demonstrate our method's efficacy in managing generation distribution while preserving image quality. We also dissect the discovered model mechanism, revealing different intrinsic features controlling fine-grained aspects of generation, boosting further research on mechanistic interpretability of diffusion models.