Caoyun Fan

Caoyun Fan

Auto-generated profile, based on publicly available information

Caoyun Fan

MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 June 2023 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
CFCaoyun Fan
Caoyun Fan
WCWenqing Chen
Wenqing Chen
JTJidong Tian
Jidong Tian
YLYitian Li
Yitian Li
HHHao He
Hao He
YJYaohui Jin
Yaohui Jin

1 August 2021
Verified
Conference Paper
Open access
PDF file
WCWenqing Chen
Wenqing Chen
JTJidong Tian
Jidong Tian
CFCaoyun Fan
Caoyun Fan
HHHao He
Hao He
YJYaohui Jin
Yaohui Jin
Recent work for image captioning mainly followed an extract-then-generate paradigm, pre-extracting a sequence of object-based features and then formulating image captioning as a single sequence-to-sequence task. Although promising, we observed two problems in generated captions: 1) content inconsistency where models would generate contradicting facts; 2) not informative enough where models would miss parts of important information. From a causal perspective, the reason is that models have captured spurious statistical correlations between visual features and certain expressions (e.g., visual features of "long hair" and "woman"). In this paper, we propose a dependent multi-task learning framework with the causal intervention (DMTCI). Firstly, we involve an intermediate task, bag-of-categories generation, before the final task, image captioning. The intermediate task would help the model better understand the visual features and thus alleviate the content inconsistency problem. Secondly, we apply Pearl's do-calculus on the model, cutting off the link between the visual features and possible confounders and thus letting models focus on the causal visual features. Specifically, the high-frequency concept set is considered as the proxy confounders where the real confounders are inferred in the continuous space. Finally, we use a multi-agent reinforcement learning (MARL) strategy to enable end-to-end training and reduce the inter-task error accumulations. The extensive experiments show that our model outperforms the baseline models and achieves competitive performance with state-of-the-art models.

11 October 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
CFCaoyun Fan
Caoyun Fan
WCWenqing Chen
Wenqing Chen
JTJidong Tian
Jidong Tian
YLYitian Li
Yitian Li
HHHao He
Hao He
YJYaohui Jin
Yaohui Jin


1 January 2023
Verified
Conference Paper
Open access
PDF file
YLYitian Li
Yitian Li
JTJidong Tian
Jidong Tian
CFCaoyun Fan
Caoyun Fan
WCWenqing Chen
Wenqing Chen
HHHao He
Hao He
YJYaohui Jin
Yaohui Jin
Yitian Li, Jidong Tian, Caoyun Fan, Wenqing Chen, Hao He, Yaohui Jin. Findings of the Association for Computational Linguistics: ACL 2023. 2023.

11 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
CFCaoyun Fan
Caoyun Fan
WCWenqing Chen
Wenqing Chen
JTJidong Tian
Jidong Tian
YLYitian Li
Yitian Li
HHHao He
Hao He
YJYaohui Jin
Yaohui Jin
Multi-Label Text Classification (MLTC) aims to assign the most relevant labels to each given text. Existing methods demonstrate that label dependency can help to improve the model's performance. However, the introduction of label dependency may cause the model to suffer from unwanted prediction bias. In this study, we attribute the bias to the model's misuse of label dependency, i.e., the model tends to utilize the correlation shortcut in label dependency rather than fusing text information and label dependency for prediction. Motivated by causal inference, we propose a CounterFactual Text Classifier (CFTC) to eliminate the correlation bias, and make causality-based predictions. Specifically, our CFTC first adopts the predict-then-modify backbone to extract precise label information embedded in label dependency, then blocks the correlation shortcut through the counterfactual de-bias technique with the help of the human causal graph. Experimental results on three datasets demonstrate that our CFTC significantly outperforms the baselines and effectively eliminates the correlation bias in datasets.