Author name cluster

Feifan Yang

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.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

Tabular Learnwares Can Be Repurposed for Seemingly Irrelevant New Tasks

Peng Tan
Feifan Yang
Zhi-Hao Tan
Zhi-Hua Zhou

The learnware paradigm aims to help users solve new tasks by reusing existing models rather than starting from scratch. A learnware consists of a model and the specification describing its capabilities. Numerous learnwares are accommodated by the learnware dock system. When users solve tasks with the system, learnwares that fully match the user task are often scarce or unavailable. This paper focuses on tabular classification tasks and explores reusing learnwares for new user tasks with significantly different feature and label spaces, leveraging the potential of numerous existing specialized tabular models developed for various tasks. Under the learnware paradigm, we find that tabular learnwares that seem semantically irrelevant can sometimes be beneficial for new user tasks. The proposed method relies solely on model-predicted probabilities and does not require gradient information, making it applicable to a wide range of tabular models. Experiments suggest that tabular learnwares can be reused beyond their original purpose across heterogeneous tasks.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Focus On What Matters: Separated Models For Visual-Based RL Generalization

Di Zhang
Bowen Lv
Hai Zhang
Feifan Yang
Junqiao Zhao
Hang Yu
Chang Huang
Hongtu Zhou

A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image reconstruction due to concerns about exacerbating overfitting to task-irrelevant features during training. Perceiving the pre-eminence of image reconstruction in representation learning, we propose SMG (\blue{S}eparated \blue{M}odels for \blue{G}eneralization), a novel approach that exploits image reconstruction for generalization. SMG introduces two model branches to extract task-relevant and task-irrelevant representations separately from visual observations via cooperatively reconstruction. Built upon this architecture, we further emphasize the importance of task-relevant features for generalization. Specifically, SMG incorporates two additional consistency losses to guide the agent's focus toward task-relevant areas across different scenarios, thereby achieving free from overfitting. Extensive experiments in DMC demonstrate the SOTA performance of SMG in generalization, particularly excelling in video-background settings. Evaluations on robotic manipulation tasks further confirm the robustness of SMG in real-world applications. Source code is available at \url{https: //anonymous. 4open. science/r/SMG/}.

PDF Details DOI

EAAI Journal 2023 Journal Article

Product online multidimensional ratings aggregation decision-making model based on group division and attribute interaction

Yi Yang
Feifan Yang
Guodong Yi
Danxia Xia
Jieyue Li

The aim of this paper is to develop a novel approach to product online ratings aggregation decision-making, which can provide method support for consumers to obtain useful decision-making knowledge and more credible product ranking results. First, the personalized characteristics contained in the information disclosed by rating individual user are mined to establish the credibility model supporting individual weight allocation, and the multi-level division mechanism is designed to propose the aggregation method of group ratings. Then, the intuitionistic fuzzy improved normalized Bonferroni mean with weighted interaction (IFINWIBM) operator is defined, which can apply to aggregate product multidimensional ratings. Moreover, driven by expert knowledge and large-scale ratings, the learning mechanism of operator parameters is designed to describe the degree of interaction between attributes, which can avoid the unscientific caused by subjectivity. We further develop an online multidimensional ratings aggregation decision-making model to solve the product ranking problem. Finally, a numerical example and comparative analysis are given to illustrate the feasibility and advantages of the proposed method, which can reduce the interference of false groups on large-scale information aggregation and improve the rationality of attribute interaction coefficient acquisition.

Details DOI

AAAI Conference 2021 Conference Paper

Multi-Document Transformer for Personality Detection

Feifan Yang
Xiaojun Quan
Yunyi Yang
Jianxing Yu

Personality detection aims to identify the personality traits implied in social media posts. The core of this task is to put together information in multiple scattered posts to depict an overall personality profile for each user. Existing approaches either encode each post individually or assemble posts arbitrarily into a new document that can be encoded sequentially or hierarchically. While the first approach ignores the connection between posts, the second tends to introduce unnecessary post-order bias into posts. In this paper, we propose a multidocument Transformer, namely Transformer-MD, to tackle the above issues. When encoding each post, Transformer-MD allows access to information in the other posts of the user through Transformer-XL’s memory tokens which share the same position embedding. Besides, personality is usually defined along different traits and each trait may need to attend to different post information, which has rarely been touched by existing research. To address this concern, we propose a dimension attention mechanism on top of Transformer-MD to obtain trait-specific representations for multi-trait personality detection. We evaluate the proposed model on the Kaggle and Pandora MBTI datasets and the experimental results show that it compares favorably with baseline methods.

PDF Details