MIT Open Access Articles: Recent submissions

Now showing items 43-45 of 54145

    • RL4CO: An Extensive Reinforcement Learning for Combinatorial Optimization Benchmark 

      Berto, Federico; Hua, Chuanbo; Park, Junyoung; Luttmann, Laurin; Ma, Yining; e.a. (ACM|Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, 2025-08-03)
      Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant ...

    • SPARTA: An Optimization Framework for Differentially Private Sparse Fine-Tuning 

      Makni, Mehdi; Behdin, Kayhan; Afriat, Gabriel; Xu, Zheng; Vassilvitskii, Sergei; e.a. (ACM|Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, 2025-08-03)
      Differentially private stochastic gradient descent (DP-SGD) is broadly considered to be the gold standard for training and fine-tuning neural networks under differential privacy (DP). With the increasing availability of ...

    • When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark 

      Lin, Junhong; Guo, Xiaojie; Zhang, Shuaicheng; Zhu, Yada; Shun, Julian (ACM|Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, 2025-08-03)
      Graph mining has become crucial in fields such as social science, finance, and cybersecurity. Many large-scale real-world networks exhibit both heterogeneity, where multiple node and edge types exist in the graph, and ...