Large-scale job scheduling is a classic problem in computing systems and industrial operations, where complex workloads, workflows, or ordered job operations must be assigned to computing nodes or machines under resource, precedence, and availability constraints. Existing solvers can provide useful reference solutions, but their search cost is often too high for time-sensitive scheduling. Recent reinforcement-learning (RL) schedulers offer faster inference, yet many rely on limited state representations, which can weaken action scoring as scheduling instances scale. In this paper, we propose ReLA, an RL scheduler built on structured representation learning and aggregation. ReLA learns intra-entity representations using self-attention and convolution, captures inter-entity operation–machine interactions using cross-attention, and aggregates multi-scale representations for parallel actor-based scoring of feasible actions. Experiments on synthetic and public scheduling benchmarks show that ReLA achieves the best makespan in most tested settings. On small and medium instances, ReLA achieves a 7.3% average optimality gap and reduces the state-of-the-art (SOTA) baseline gap by 13.0%. On large instances with at least a hundred jobs, ReLA reduces the SOTA gap by 78.6%, with an average gap of 2.1%. These results demonstrate ReLA’s effectiveness for scalable and runtime-efficient scheduling over large action spaces.
Zheng-Yi Kwan, Wei Zhang, Aik Beng Ng et al.· 0 citations
Advances in real-world adversarial threats have heightened concerns over the privacy and security of AI systems. One key threat is Data Poisoning, where malicious data is injected into training sets or model inputs to compromise model behavior. While much of the current research focuses on deep learning, particularly Foundation Models such as Large Language Models, there is limited understanding of how data poisoning affects different model eras. This survey presents a comparative analysis of data poisoning vulnerabilities in different model eras: statistical machine learning models, smaller-scale ”classical” deep learning models, and foundation models. Our goal is to inform practitioners of the trade-offs between robustness and performance when choosing models for different applications.
Jia Yi Chan, Huaqun Guo, Timothy Liu et al.· Singapore Institute of Techn...· 0 citations
Advances in real-world adversarial threats have heightened concerns over the privacy and security of AI systems. One key threat is Data Poisoning, where malicious data is injected into training sets or model inputs to compromise model behavior. While much of the current research focuses on deep learning, particularly Foundation Models such as Large Language Models, there is limited understanding of how data poisoning affects different model eras. This survey presents a comparative analysis of data poisoning vulnerabilities in different model eras: statistical machine learning models, smaller-scale ”classical” deep learning models, and foundation models. Our goal is to inform practitioners of the trade-offs between robustness and performance when choosing models for different applications.
Jia Yi Chan, Huaqun Guo, Timothy Liu et al.· Singapore Institute of Techn...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
