Alleviating the estimation bias of deep deterministic policy gradient via co-regularization

Li, Yao; Wang, Yuhui; Gan, YaoZhong; Tan, Xiaoyang

doi:10.1016/j.patcog.2022.108872

Cited by 7 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In consequence, this entangles topics at all levels to cover the same semantic granularity, causing low rationality. The second type is aggregation decoders (Chen et al 2021b,a;Li et al 2022;Chen et al 2023). Their decoding involves all levels, which still entangles topics at all levels.…”

Section: Context-aware Disentangled Decodermentioning

confidence: 99%

“…Second, to solve the low rationality issue, we further propose a novel Context-aware Disentangled Decoder (CDD). Rather than entangled decoding in early work (Chen et al 2021a(Chen et al , 2023Li et al 2022), CDD decodes input documents using topics at each level individually, leading to disentangled decoding. In addition, the decoding of each level incorporates a bias containing topical semantics from its contextual levels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling

Wu,

Pan,

Nguyen

et al. 2024

AAAI

View full text Add to dashboard Cite

Hierarchical topic modeling aims to discover latent topics from a corpus and organize them into a hierarchy to understand documents with desirable semantic granularity. However, existing work struggles with producing topic hierarchies of low affinity, rationality, and diversity, which hampers document understanding. To overcome these challenges, we in this paper propose Transport Plan and Context-aware Hierarchical Topic Model (TraCo). Instead of early simple topic dependencies, we propose a transport plan dependency method. It constrains dependencies to ensure their sparsity and balance, and also regularizes topic hierarchy building with them. This improves affinity and diversity of hierarchies. We further propose a context-aware disentangled decoder. Rather than previously entangled decoding, it distributes different semantic granularity to topics at different levels by disentangled decoding. This facilitates the rationality of hierarchies. Experiments on benchmark datasets demonstrate that our method surpasses state-of-the-art baselines, effectively improving the affinity, rationality, and diversity of hierarchical topic modeling with better performance on downstream tasks.

show abstract

Section: Context-aware Disentangled Decodermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%