Many modern recommender systems represent user and item attributes as embedding vectors, relying on them for accurate recommendations. However, entangled embeddings often capture not only intrinsic property factors (e.g., user interest in item property) but also popularity factors (e.g., user conformity to item popularity) indistinguishably. These embeddings, influenced by popularity distribution, may face challenges when the popularity distribution at test time differs from historical distribution. Existing remedies in the literature involve disentangled embedding learning, which aims to separately capture intrinsic and popularity factors, demonstrating plausible generalization during popularity distribution shifts. However, we highlight that these methods often overlook a crucial aspect of popularity shifts-their temporal nature-in both training and inference phases. To address this, we propose Temporal Popularity distribution shift generalizABle recommender system (TPAB), a novel disentanglement framework incorporating temporal popularity. TPAB introduce a new (1) temporal-aware embedding design for users and items. Within this design, (2) popularity coarsening and (3) popularity bootstrapping are proposed to enhance generalization further. We also provide theoretical analysis showing that the bootstrapping loss eliminates the effect of popularity on the learned model. During inference, we infer test-time popularity and corresponding embeddings, using them alongside property embeddings for prediction. Extensive experiments on real-world datasets validate TPAB, showcasing its outstanding generalization ability during temporal popularity distribution shifts.

In the era of big data and AI, recommender systems must adapt to evolving user preferences and new users/items to maintain high-quality recommendations. Fine-tuning, which updates model parameters using only new data, offers an efficient alternative to full retraining but struggles to balance stability (retaining past knowledge) and plasticity (adapting to new knowledge). While existing methods prioritize stability to address catastrophic forgetting, we argue that plasticity must also be explicitly strengthened, especially for users with rapidly changing preferences. In this work, we propose PlastIcity and StAbility balancing continual recommender systems (PISA), a novel framework that adaptively balances stability and plasticity based on user preference shifts. PISA quantifies preference shifts as changes in user distances to item clusters, and then guides user embeddings by prioritizing stability for stable users and plasticity for dynamic users. To achieve this, PISA leverages backward knowledge from the previous model and forward knowledge from fine-tuning on current data. During training, PISA maximizes mutual information between user-specific parameters and the relevant reference knowledge. Theoretically, we show that enhancing plasticity mitigates distribution shifts more effectively than fine-tuning alone. Empirically, extensive experiments on three real-world datasets validate PISA's superiority over existing methods and highlight the contributions of its components.

Software-Defined Wide Area Networks (SD-WAN) have emerged as a transformative technology for modern enterprise networks, providing increased flexibility and costefficiency. However, ensuring network reliability and minimizing downtime remain significant challenges in SD-WAN deployments. Traditional fault management methods typically rely on reactive approaches, where network issues are addressed after they occur. In this paper, we present Semantic FaultAware (SFA) architecture to enable proactive fault prediction for SD-WAN, which is a novel framework that leverages semantic knowledge graphs and machine learning techniques. To facilitate a deeper understanding of network behavior and fault patterns, the SFA architecture integrates a semantic layer above the control plane. Moreover, a semantic-based knowledge graph construction approach is introduced to harness better representations of monitoring metric entities and relationships in a network. Finally, we propose graphical embedding techniques to enhance the process of feature engineering and machine learning, thereby enabling the accurate prediction of potential network faults. Experimental evaluations conducted on real-world SD-WAN network monitoring data validate the effectiveness of the SFA architecture in proactive fault prediction. The results demonstrate its superior accuracy enhancement in predicting faults ahead of time, enabling network operators to proactively manage and maintain the network infrastructure.

User-side group fairness is crucial for modern recommender systems, alleviating performance disparities among user groups defined by sensitive attributes like gender, race, or age. In the everevolving landscape of user-item interactions, continual adaptation to newly collected data is crucial for recommender systems to stay aligned with the latest user preferences. However, we observe that such continual adaptation often worsen performance disparities. This necessitates a thorough investigation into user-side fairness in dynamic recommender systems. This problem is challenging due to distribution shifts, frequent model updates, and nondifferentiability of ranking metrics. To our knowledge, this paper presents the first principled study on ensuring user-side fairness in dynamic recommender systems. We start with theoretical analyses on fine-tuning v.s. retraining, showing that the best practice is incremental fine-tuning with restart. Guided by our theoretical analyses, we propose FAir Dynamic rEcommender (FADE), an end-to-end fine-tuning framework to dynamically ensure user-side fairness over time. To overcome the non-differentiability of recommendation metrics in the fairness loss, we further introduce Differentiable Hit (DH) as an improvement over the recent NeuralNDCG method, not only alleviating its gradient vanishing issue but also achieving higher efficiency. Besides that, we also address the instability issue of the fairness loss by leveraging the competing nature between the recommendation loss and the fairness loss. Through extensive experiments on real-world datasets, we demonstrate that FADE effectively and efficiently reduces performance disparities with little sacrifice in the overall recommendation performance.