Women are twice as likely as men to face online harassment due to their gender. Despite recent advances in multimodal content moderation, most approaches still overlook the social dynamics behind this phenomenon, where perpetrators reinforce prejudices and group identity within like-minded communities. Graph-based methods offer a promising way to capture such interactions, yet existing solutions remain limited by heuristic graph construction, shallow modality fusion, and instance-level reasoning. In this work, we present MemeWeaver, an end-to-end trainable multimodal framework for detecting sexism and misogyny through a novel inter-meme graph reasoning mechanism. We systematically evaluate multiple visual--textual fusion strategies and show that our approach consistently outperforms state-of-the-art baselines on the MAMI and EXIST benchmarks, while achieving faster training convergence. Further analyses reveal that the learned graph structure captures semantically meaningful patterns, offering valuable insights into the relational nature of online hate.

翻译：女性因其性别而遭受网络骚扰的可能性是男性的两倍。尽管多模态内容审核领域近期取得了进展，但大多数方法仍忽视了这一现象背后的社会动态，即施害者在志同道合的社区内强化偏见与群体认同。基于图的方法为捕捉此类互动提供了有前景的途径，然而现有解决方案仍受限于启发式图构建、浅层模态融合和实例级推理。在本研究中，我们提出了 MemeWeaver——一种端到端可训练的多模态框架，通过新颖的模因间图推理机制来检测性别歧视与厌女症。我们系统评估了多种视觉-文本融合策略，结果表明，在 MAMI 和 EXIST 基准测试中，我们的方法始终优于最先进的基线模型，同时实现了更快的训练收敛。进一步分析表明，学习到的图结构捕捉到了具有语义意义的模式，为理解网络仇恨的关系本质提供了有价值的洞见。