SIMBA is a diffusion-model-agnostic framework pairing a lightweight neural surrogate with direct discrete search that drastically cuts time-to-solution while achieving superior influence spread and data efficiency.
Abstract
Existing learning-based influence maximization frameworks rely heavily on complex neural architectures and continuous optimization over seed representations. We challenge this paradigm with SIMBA, a diffusion-model-agnostic framework pairing a lightweight neural surrogate with direct discrete search. SIMBA introduces three key components: 1) uniformly anchored node embeddings that eliminate initialization noise and encourage learning driven by graph topology and diffusion pattern, 2) a shallow two-layer graph neural network surrogate predicting final infection states, and 3) batched multi-swap simulated annealing that explores combinatorial seed space without gradients or continuous relaxation. By shifting compute from complex representation learning to effective discrete search, SIMBA drastically cuts time-to-solution while achieving superior influence spread and data efficiency. Our code is available at https://github.com/yl489/rethink-IM.
Constructive neural combinatorial optimization (NCO) has emerged as a promising paradigm that learns to construct solutions to combinatorial optimization problems (COPs) step by step, which reduces reliance on handcrafted rules and enables fast inference. While many methods with dynamic embeddings generalize well, they...
Chang-Liang Zhou, Yuan-Yao Chen, Rong-Sheng Chen et al.· 0 citations
ProtoGuide is introduced, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism for discrete diffusion models and raises macro classification accuracy and outperforms DiGress's built-in conditional training under the authors' configuration.
Salvatore Romano, Marco Grassia, Pietro Liò et al.· 0 citations
Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a co-sampled solution group. Preference-optimization methods anchor on the single best solution and discard fine-grained quality and structural signal from...
Yuan-Yu Li, Jin-Tao Xu, Zijiang Liu et al.· 0 citations
Discrete diffusion models have emerged as a powerful paradigm for solving combinatorial optimization (CO) problems on graphs by learning to sample high-quality solutions. A common inference-time approach is to generate multiple candidate solutions independently and return the best-performing sample, improving solution...
Arman Mielke, Uwe Bauknecht, Thilo Strauss et al.· 0 citations
Differentiable Hierarchical Fusion is presented, a novel framework that merges reasoning models with efficient base models via differentiable optimization to produce concise, accurate outputs and introduces a dual-factor adaptive weighting mechanism to capture intra-block variance and inter-block importance hierarchies...
Chuan-Gen Gao, Wen-Lun Zhang, Shang-Kun Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
Stable Diffusion models deliver photorealistic image synthesis but face computational bottlenecks that hinder deployment in resource-constrained environments. However, most existing distillation methods for diffusion models rely on point-wise feature matching, which often fails to preserve global semantic structure, or...
Bich-Nga Pham, Quoc-Truong Truong, Anh-Khoa Nguyen Vu et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
