Search Results for author: Feng Ji

Found 47 papers, 9 papers with code

Frequency Convergence of Complexon Shift Operators (Extended Version)

no code implementations12 Sep 2023 Purui Zhang, Xingchao Jian, Feng Ji, Wee Peng Tay, Bihan Wen

We recall the notion of a complexon as the limit of a simplicial complex sequence.

Distribution shift mitigation at test time with performance guarantees

no code implementations18 Aug 2023 Rui Ding, Jielong Yang, Feng Ji, Xionghu Zhong, Linbo Xie

To address this challenge, we propose FR-GNN, a general framework for GNNs to conduct feature reconstruction.

The faces of Convolution: from the Fourier theory to algebraic signal processing

no code implementations16 Jul 2023 Feng Ji, Wee Peng Tay, Antonio Ortega

In this expository article, we provide a self-contained overview of the notion of convolution embedded in different theories: from the classical Fourier theory to the theory of algebraic signal processing.

AMTSS: An Adaptive Multi-Teacher Single-Student Knowledge Distillation Framework For Multilingual Language Inference

no code implementations13 May 2023 Qianglong Chen, Feng Ji, Feng-Lin Li, Guohai Xu, Ming Yan, Ji Zhang, Yin Zhang

To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptive multi-teacher single-student distillation framework, which allows distilling knowledge from multiple teachers to a single student.

Knowledge Distillation

Generalized signals on simplicial complexes

no code implementations11 May 2023 Xingchao Jian, Feng Ji, Wee Peng Tay

Topological signal processing (TSP) over simplicial complexes typically assumes observations associated with the simplicial complexes are real scalars.

Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks

1 code implementation29 Apr 2023 Feng Ji, See Hian Lee, Hanyang Meng, Kai Zhao, Jielong Yang, Wee Peng Tay

We introduce the key notion of label non-uniformity, which is derived from the Wasserstein distance between the softmax distribution of the logits and the uniform distribution.

Node Classification

Distributional Signals for Node Classification in Graph Neural Networks

no code implementations7 Apr 2023 Feng Ji, See Hian Lee, Kai Zhao, Wee Peng Tay, Jielong Yang

In graph neural networks (GNNs), both node features and labels are examples of graph signals, a key notion in graph signal processing (GSP).

Classification Node Classification

Graph signal processing with categorical perspective

no code implementations24 Feb 2023 Feng Ji, Xingchao Jian, Wee Peng Tay

In this paper, we propose a framework for graph signal processing using category theory.

On distributional graph signals

no code implementations22 Feb 2023 Feng Ji, Xingchao Jian, Wee Peng Tay

We develop signal processing tools to study the new notion of distributional graph signals.

Sampling of Correlated Bandlimited Continuous Signals by Joint Time-vertex Graph Fourier Transform

no code implementations10 Oct 2022 Zhongyi Ni, Feng Ji, Hang Sheng, Hui Feng, Bo Hu

When sampling multiple signals, the correlation between the signals can be exploited to reduce the overall number of samples.

On semi shift invariant graph filters

no code implementations28 Sep 2022 Feng Ji, See Hian Lee, Wee Peng Tay

In graph signal processing, one of the most important subjects is the study of filters, i. e., linear transformations that capture relations between graph signals.

SGAT: Simplicial Graph Attention Network

1 code implementation24 Jul 2022 See Hian Lee, Feng Ji, Wee Peng Tay

In this paper, we present Simplicial Graph Attention Network (SGAT), a simplicial complex approach to represent such high-order interactions by placing features from non-target nodes on the simplices.

Graph Attention Graph Learning +1

Abstract message passing and distributed graph signal processing

no code implementations9 Jun 2022 Feng Ji, Yiqi Lu, Wee Peng Tay, Edwin Chong

Graph signal processing is a framework to handle graph structured data.

To further understand graph signals

no code implementations2 Mar 2022 Feng Ji, Wee Peng Tay

Graph signal processing (GSP) is a framework to analyze and process graph-structured data.

Recovery of Graph Signals from Sign Measurements

no code implementations26 Sep 2021 Wenwei Liu, Hui Feng, Kaixuan Wang, Feng Ji, Bo Hu

Sampling and interpolation have been extensively studied, in order to reconstruct or estimate the entire graph signal from the signal values on a subset of vertexes, of which most achievements are about continuous signals.

KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference

no code implementations ACL 2021 Qianglong Chen, Feng Ji, Xiangji Zeng, Feng-Lin Li, Ji Zhang, Haiqing Chen, Yin Zhang

In order to better understand the reason behind model behaviors (i. e., making predictions), most recent works have exploited generative models to provide complementary explanations.

Language Modelling Natural Language Inference

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss

1 code implementation5 May 2021 Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, Alberto del Bimbo

Experimental results demonstrate that our adapted margin cosine loss can greatly enhance the baseline models with an absolute performance gain of 15\% on average, strongly verifying the potential of tackling the language prior problem in VQA from the angle of the answer feature space learning.

Question Answering Visual Question Answering

Signal processing with a distribution of graph operators

no code implementations11 Dec 2020 Feng Ji, Wee Peng Tay

In this paper, we develop a signal processing framework of a network without explicit knowledge of the network topology.

Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations

no code implementations25 Nov 2020 Haojie Pan, Cen Chen, Chengyu Wang, Minghui Qiu, Liu Yang, Feng Ji, Jun Huang

More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses.

Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

no code implementations COLING 2020 Qianglong Chen, Feng Ji, Haiqing Chen, Yin Zhang

More concretely, we first introduce a novel graph-based iterative knowledge retrieval module, which iteratively retrieves concepts and entities related to the given question and its choices from multiple knowledge sources.

Language Modelling Natural Language Understanding +2

AliMe KG: Domain Knowledge Graph Construction and Application in E-commerce

no code implementations24 Sep 2020 Feng-Lin Li, Hehong Chen, Guohai Xu, Tian Qiu, Feng Ji, Ji Zhang, Haiqing Chen

Pre-sales customer service is of importance to E-commerce platforms as it contributes to optimizing customers' buying process.

graph construction Question Answering

Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems

no code implementations27 May 2020 Zehao Lin, Shaobo Cui, Guodun Li, Xiaoming Kang, Feng Ji, FengLin Li, Zhongzhou Zhao, Haiqing Chen, Yin Zhang

More specifically, we take advantage of a decision model to help the dialogue system decide whether to wait or answer.

MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert

no code implementations21 May 2020 Shuke Peng, Feng Ji, Zehao Lin, Shaobo Cui, Haiqing Chen, Yin Zhang

How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response.

Subgraph Signal Processing

no code implementations11 May 2020 Feng Ji, Wee Peng Tay, Giacomo Kahn

Graph signal processing, like the graph Fourier transform, requires the full graph signal at every vertex of the graph.

Signal processing on simplicial complexes

no code implementations6 Apr 2020 Feng Ji, Giacomo Kahn, Wee Peng Tay

In this paper, we develop a signal processing framework on simplicial complexes, such that we recover the traditional GSP theory when restricted to signals on graphs.

Query-bag Matching with Mutual Coverage for Information-seeking Conversations in E-commerce

1 code implementation7 Nov 2019 Zhenxin Fu, Feng Ji, Wenpeng Hu, Wei Zhou, Dongyan Zhao, Haiqing Chen, Rui Yan

Information-seeking conversation system aims at satisfying the information needs of users through conversations.

Text Matching

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks

no code implementations IJCNLP 2019 Zehao Lin, Xinjing Huang, Feng Ji, Haiqing Chen, Ying Zhang

How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans.

Learning from Positive and Unlabeled Data with Adversarial Training

no code implementations25 Sep 2019 Wenpeng Hu, Ran Le, Bing Liu, Feng Ji, Haiqing Chen, Dongyan Zhao, Jinwen Ma, Rui Yan

Positive-unlabeled (PU) learning learns a binary classifier using only positive and unlabeled examples without labeled negative examples.

Review-Driven Answer Generation for Product-Related Questions in E-Commerce

1 code implementation27 Apr 2019 Shiqian Chen, Chenliang Li, Feng Ji, Wei Zhou, Haiqing Chen

Then, we devise a mechanism to identify the relevant information from the noise-prone review snippets and incorporate this information to guide the answer generation.

Answer Generation

GFCN: A New Graph Convolutional Network Based on Parallel Flows

no code implementations25 Feb 2019 Feng Ji, Jielong Yang, Qiang Zhang, Wee Peng Tay

In view of the huge success of convolution neural networks (CNN) for image classification and object recognition, there have been attempts to generalize the method to general graph-structured data.

General Classification Image Classification +1

Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching

no code implementations30 Dec 2018 Chen Qu, Feng Ji, Minghui Qiu, Liu Yang, Zhiyu Min, Haiqing Chen, Jun Huang, W. Bruce Croft

Specifically, the data selector "acts" on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide "rewards" in turn to update the selector.

Information Retrieval Natural Language Inference +5

Improving Multilingual Semantic Textual Similarity with Shared Sentence Encoder for Low-resource Languages

no code implementations20 Oct 2018 Xin Tang, Shanbo Cheng, Loc Do, Zhiyu Min, Feng Ji, Heng Yu, Ji Zhang, Haiqin Chen

Our approach is extended from a basic monolingual STS framework to a shared multilingual encoder pretrained with translation task to incorporate rich-resource language data.

Machine Translation Semantic Similarity +3

A Deep Relevance Model for Zero-Shot Document Filtering

1 code implementation ACL 2018 Chenliang Li, Wei Zhou, Feng Ji, Yu Duan, Haiqing Chen

In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand.

Sentiment Analysis Text Classification +1

Memory-augmented Dialogue Management for Task-oriented Dialogue Systems

no code implementations1 May 2018 Zheng Zhang, Minlie Huang, Zhongzhou Zhao, Feng Ji, Haiqing Chen, Xiaoyan Zhu

Dialogue management (DM) decides the next action of a dialogue system according to the current dialogue state, and thus plays a central role in task-oriented dialogue systems.

Dialogue Management Management +1

Cannot find the paper you are looking for? You can Submit a new open access paper.