Arrow Research search

Author name cluster

Qiang Ding

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
1 author row

Possible papers

2

NeurIPS Conference 2023 Conference Paper

Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification

  • Qiang Ding
  • Yixuan Cao
  • Ping Luo

Selective classification allows a machine learning model to reject some hard inputs and thus improve the reliability of its predictions. In this area, the ensemble method is powerful in practice, but there has been no solid analysis on why the ensemble method works. Inspired by an interesting empirical result that the improvement of the ensemble largely comes from top-ambiguity samples where its member models diverge, we prove that, based on some assumptions, the ensemble has a lower selective risk than the member model for any coverage within a range. The proof is nontrivial since the selective risk is a non-convex function of the model prediction. The assumptions and the theoretical results are supported by systematic experiments on both computer vision and natural language processing tasks.

PDF Details

YNICL Journal 2016 Journal Article

The development of automatic emotion regulation in an implicit emotional Go/NoGo paradigm and the association with depressive symptoms and anhedonia during adolescence

  • Wenhai Zhang
  • Qiang Ding
  • Ning Chen
  • Qing Wei
  • Cancan Zhao
  • Ping Zhang
  • Xiying Li
  • Qiang Liu

Impaired automatic emotion regulation (AER) is closely related to major depressive disorder. Our research in adults has identified two AER-related components, Go N2 and NoGo P3, in an implicit emotional Go/NoGo paradigm. However, it is unclear whether Go N2 and NoGo P3 reflect the development of AER in adolescents and the relationship of these components with subclinical depressive symptoms and trait anhedonia. We collected EEG data from 55 adolescents while they completed the implicit emotional Go/NoGo task. After the experiment, the subjects completed the Chinese version of the Temporal Experience of Pleasure Scale and the Beck Depression Inventory. Consistent with results in adults, we determined that Go N2 represents automatic top-down attention to emotions in Go trials, whereas NoGo P3 represents automatic response inhibition in NoGo trials. These AER components exhibited age-dependent improvement during adolescence. Additionally, NoGo P3 amplitudes elicited by viewing positive faces were positively correlated with trait anhedonia, whereas NoGo P3 amplitudes elicited by viewing negative faces were negatively correlated with depressive symptoms. Our observations provide further understanding of the neurodevelopmental mechanism of AER and yield new insight into dissociable impairments in AER in adolescents with major depressive disorder during positive and negative implicit processing.

Details DOI