Arrow Research search

Author name cluster

Feng Ji

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.

18 papers
2 author rows

Possible papers

18

AAAI Conference 2026 Conference Paper

Conformal Prediction for Multi-Source Detection on a Network

  • Xingchao Jian
  • Purui Zhang
  • Lan Tian
  • Feng Ji
  • Wenfei Liang
  • Wee Peng Tay
  • Bihan Wen
  • Felix Krahmer

Detecting the origin of information or infection spread in networks is a fundamental challenge with applications in misinformation tracking, epidemiology, and beyond. We study the multi-source detection problem: given snapshot observations of node infection status on a graph, estimate the set of source nodes that initiated the propagation. Existing methods either lack statistical guarantees or are limited to specific diffusion models and assumptions. We propose a novel conformal prediction framework that provides statistically valid recall guarantees for source set detection, independent of the underlying diffusion process or data distribution. Our approach introduces principled score functions to quantify the alignment between predicted probabilities and true sources, and leverages a calibration set to construct prediction sets with user-specified recall and coverage levels. The method is applicable to both single- and multi-source scenarios, supports general network diffusion dynamics, and is computationally efficient for large graphs. Empirical results demonstrate that our method achieves rigorous coverage with competitive accuracy, outperforming existing baselines in both reliability and scalability.

PDF Details DOI

TMLR Journal 2026 Journal Article

Explainable Error Detection in Integrated Circuits Image Segmentation via Graph Neural Networks

  • MA XIAOYU
  • Jingyang Dai
  • Feng Ji
  • Deruo Cheng
  • Yiqiong Shi
  • Bah-Hwee Gwee

Automated segmentation of integrated circuit (IC) images plays a critical role in hardware assurance, yet remains challenging due to nanoscale structural complexity, extremely low error tolerance, and the limited interpretability of existing deep learning–based approaches. Most convolutional neural network (CNN)–based error detection methods operate at the whole-image level, making it difficult to localize specific faults or explain their structural causes. In this work, we propose an explainable graph neural network (GNN) framework for component-level error detection in IC segmentation masks. Each connected component in the binary mask is converted into a feature-annotated graph that captures both topological connectivity and geometric properties. Error detection is then formulated as graph-based classification, enabling the identification of anomalous components and precise localization of erroneous regions. Experiments on multiple IC layouts under diverse imaging conditions demonstrate that the proposed method achieves robust and generalizable performance. In addition to accurate detection, the graph-based formulation provides improved interpretability by explicitly linking predictions to structural deviations at the component level.

PDF Details

AAAI Conference 2025 Conference Paper

Falcon: Faster and Parallel Inference of Large Language Models Through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Tree

  • Xiangxiang Gao
  • Weisheng Xie
  • Yiwei Xiang
  • Feng Ji

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon, an innovative semi-autoregressive speculative decoding framework fashioned to augment both the drafter's parallelism and output quality. Falcon incorporates the Coupled Sequential Glancing Distillation technique, which fortifies inter-token dependencies within the same block, leading to increased speculation accuracy. We offer a comprehensive theoretical analysis to illuminate the underlying mechanisms. Additionally, we introduce a Custom-Designed Decoding Tree, which permits the drafter to generate multiple tokens in a single forward pass and accommodates multiple forward passes as needed, thereby boosting the number of drafted tokens and significantly improving the overall acceptance rate. Comprehensive evaluations on benchmark datasets such as MT-Bench, HumanEval, and GSM8K demonstrate Falcon's superior acceleration capabilities. The framework achieves a lossless speedup ratio ranging from 2.91x to 3.51x when tested on the Vicuna and LLaMA2-Chat model series. These results outstrip existing speculative decoding methods for LLMs, including Eagle, Medusa, Lookahead, SPS, and PLD, while maintaining a compact drafter architecture equivalent to merely two Transformer layers.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Rethinking Graph Neural Networks From A Geometric Perspective Of Node Features

  • Feng Ji
  • Yanan Zhao 0003
  • Kai Zhao 0010
  • Hanyang Meng
  • Jielong Yang
  • Wee Peng Tay

Many works on graph neural networks (GNNs) focus on graph topologies and analyze graph-related operations to enhance performance on tasks such as node classification. In this paper, we propose to understand GNNs based on a feature-centric approach. Our main idea is to treat the features of nodes from each label class as a whole, from which we can identify the centroid. The convex hull of these centroids forms a simplex called the feature centroid simplex, where a simplex is a high-dimensional generalization of a triangle. We borrow ideas from coarse geometry to analyze the geometric properties of the feature centroid simplex by comparing them with basic geometric models, such as regular simplexes and degenerate simplexes. Such a simplex provides a simple platform to understand graph-based feature aggregation, including phenomena such as heterophily, oversmoothing, and feature re-shuffling. Based on the theory, we also identify simple and useful tricks for the node classification task.

Details

NeurIPS Conference 2024 Conference Paper

Distributed-Order Fractional Graph Operating Network

  • Kai Zhao
  • Xuhao Li
  • Qiyu Kang
  • Feng Ji
  • Qinxu Ding
  • Yanan Zhao
  • Wenfei Liang
  • Wee Peng Tay

We introduce the Distributed-order fRActional Graph Operating Network (DRAGON), a novel continuous Graph Neural Network (GNN) framework that incorporates distributed-order fractional calculus. Unlike traditional continuous GNNs that utilize integer-order or single fractional-order differential equations, DRAGON uses a learnable probability distribution over a range of real numbers for the derivative orders. By allowing a flexible and learnable superposition of multiple derivative orders, our framework captures complex graph feature updating dynamics beyond the reach of conventional models. We provide a comprehensive interpretation of our framework's capability to capture intricate dynamics through the lens of a non-Markovian graph random walk with node feature updating driven by an anomalous diffusion process over the graph. Furthermore, to highlight the versatility of the DRAGON framework, we conduct empirical evaluations across a range of graph learning tasks. The results consistently demonstrate superior performance when compared to traditional continuous GNN models. The implementation code is available at \url{https: //github. com/zknus/NeurIPS-2024-DRAGON}.

PDF Details DOI

ICML Conference 2024 Conference Paper

Graph Neural Networks with a Distribution of Parametrized Graphs

  • See Hian Lee
  • Feng Ji
  • Kelin Xia
  • Wee Peng Tay

Traditionally, graph neural networks have been trained using a single observed graph. However, the observed graph represents only one possible realization. In many applications, the graph may encounter uncertainties, such as having erroneous or missing edges, as well as edge weights that provide little informative value. To address these challenges and capture additional information previously absent in the observed graph, we introduce latent variables to parameterize and generate multiple graphs. The parameters follow an unknown distribution to be estimated. We propose a formulation in terms of maximum likelihood estimation of the network parameters. Therefore, it is possible to devise an algorithm based on Expectation-Maximization (EM). Specifically, we iteratively determine the distribution of the graphs using a Markov Chain Monte Carlo (MCMC) method, incorporating the principles of PAC-Bayesian theory. Numerical experiments demonstrate improvements in performance against baseline models on node classification for both heterogeneous and homogeneous graphs.

Details

TMLR Journal 2024 Journal Article

Heterogeneous graph adaptive flow network

  • Lu Yiqi
  • Feng Ji
  • Wee Peng Tay

Many graphs or networks are heterogeneous by nature, involving various vertex types and relation types. Most graph learning models for heterogeneous graphs employ meta-paths to guide neighbor selections and extract composite relations. However, the use of meta-paths to generate relations between the same vertex types may result in directed edges and failure to fully utilize the other vertex or edge types in the data. To address such a limitation, we propose Heterogeneous graph adaptive flow network (HetaFlow), which removes the need for meta-paths. HetaFlow decomposes the heterogeneous graph into flows and performs convolution across heterogeneous vertex and edge types, using an adaptation to change the vertex features based on the corresponding vertex and edge types during aggregation. Experiments on real-world datasets for vertex clustering and vertex classification demonstrate that HetaFlow outperforms other benchmark models and achieves state-of-the-art performance on commonly used benchmark datasets. The codes are available at https://github.com/AnonymizedC/HetaFlow.

PDF Details

TMLR Journal 2024 Journal Article

Node-Specific Space Selection via Localized Geometric Hyperbolicity in Graph Neural Networks

  • See Hian Lee
  • Feng Ji
  • Wee Peng Tay

Many graph neural networks have been developed to learn graph representations in either Euclidean or hyperbolic space, with all nodes' representations embedded in a single space. However, a graph can have hyperbolic and Euclidean geometries at different regions of the graph. Thus, it is sub-optimal to indifferently embed an entire graph into a single space. In this paper, we explore and analyze two notions of local hyperbolicity, describing the underlying local geometry: geometric (Gromov) and model-based, to determine the preferred space of embedding for each node. The two hyperbolicities' distributions are aligned using the Wasserstein metric such that the calculated geometric hyperbolicity guides the choice of the learned model hyperbolicity. As such our model Joint Space Graph Neural Network (JSGNN) can leverage both Euclidean and hyperbolic spaces during learning by allowing node-specific geometry space selection. We evaluate our model on both node classification and link prediction tasks and observe promising performance compared to baseline models.

PDF Details

ICLR Conference 2024 Conference Paper

Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND

  • Qiyu Kang
  • Kai Zhao 0010
  • Qinxu Ding
  • Feng Ji
  • Xuhao Li
  • Wenfei Liang 0001
  • Yang Song 0012
  • Wee Peng Tay

We introduce the FRactional-Order graph Neural Dynamical network (FROND), a new continuous graph neural network (GNN) framework. Unlike traditional continuous GNNs that rely on integer-order differential equations, FROND employs the Caputo fractional derivative to leverage the non-local properties of fractional calculus. This approach enables the capture of long-term dependencies in feature updates, moving beyond the Markovian update mechanisms in conventional integer-order models and offering enhanced capabilities in graph representation learning. We offer an interpretation of the node feature updating process in FROND from a non-Markovian random walk perspective when the feature updating is particularly governed by a diffusion process. We demonstrate analytically that oversmoothing can be mitigated in this setting. Experimentally, we validate the FROND framework by comparing the fractional adaptations of various established integer-order continuous GNNs, demonstrating their consistently improved performance and underscoring the framework's potential as an effective extension to enhance traditional continuous GNNs. The code is available at \url{https://github.com/zknus/ICLR2024-FROND}.

Details

ICML Conference 2023 Conference Paper

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

  • Feng Ji
  • See Hian Lee
  • Hanyang Meng
  • Kai Zhao 0010
  • Jielong Yang
  • Wee Peng Tay

In node classification using graph neural networks (GNNs), a typical model generates logits for different class labels at each node. A softmax layer often outputs a label prediction based on the largest logit. We demonstrate that it is possible to infer hidden graph structural information from the dataset using these logits. 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. We demonstrate that nodes with small label non-uniformity are harder to classify correctly. We theoretically analyze how the label non-uniformity varies across the graph, which provides insights into boosting the model performance: increasing training samples with high non-uniformity or dropping edges to reduce the maximal cut size of the node set of small non-uniformity. These mechanisms can be easily added to a base GNN model. Experimental results demonstrate that our approach improves the performance of many benchmark base models.

Details

IJCAI Conference 2022 Conference Paper

SGAT: Simplicial Graph Attention Network

  • See Hian Lee
  • Feng Ji
  • Wee Peng Tay

Heterogeneous graphs have multiple node and edge types and are semantically richer than homogeneous graphs. To learn such complex semantics, many graph neural network approaches for heterogeneous graphs use metapaths to capture multi-hop interactions between nodes. Typically, features from non-target nodes are not incorporated into the learning procedure. However, there can be nonlinear, high-order interactions involving multiple nodes or edges. 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. We then use attention mechanisms and upper adjacencies to generate representations. We empirically demonstrate the efficacy of our approach with node classification tasks on heterogeneous graph datasets and further show SGAT's ability in extracting structural information by employing random node features. Numerical experiments indicate that SGAT performs better than other current state-of-the-art heterogeneous graph learning methods.

PDF Details DOI

IJCAI Conference 2021 Conference Paper

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss

  • Yangyang Guo
  • Liqiang Nie
  • Zhiyong Cheng
  • Feng Ji
  • Ji Zhang
  • Alberto Del Bimbo

A number of studies point out that current Visual Question Answering (VQA) models are severely affected by the language prior problem, which refers to blindly making predictions based on the language shortcut. Some efforts have been devoted to overcoming this issue with delicate models. However, there is no research to address it from the view of the answer feature space learning, despite the fact that existing VQA methods all cast VQA as a classification task. Inspired by this, in this work, we attempt to tackle the language prior problem from the viewpoint of the feature space learning. An adapted margin cosine loss is designed to discriminate the frequent and the sparse answer feature space under each question type properly. In this way, the limited patterns within the language modality can be largely reduced to eliminate the language priors. We apply this loss function to several baseline models and evaluate its effectiveness on two VQA-CP benchmarks. Experimental results demonstrate that our proposed adapted margin cosine loss can 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.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Predictive Adversarial Learning from Positive and Unlabeled Data

  • Wenpeng Hu
  • Ran Le
  • Bing Liu
  • Feng Ji
  • Jinwen Ma
  • Dongyan Zhao
  • Rui Yan

This paper studies learning from positive and unlabeled examples, known as PU learning. It proposes a novel PU learning method called Predictive Adversarial Networks (PAN) based on GAN (Generative Adversarial Networks). GAN learns a generator to generate data (e. g. , images) to fool a discriminator which tries to determine whether the generated data belong to a (positive) training class. PU learning can be casted as trying to identify (not generate) likely positive instances from the unlabeled set to fool a discriminator that determines whether the identified likely positive instances from the unlabeled set are indeed positive. However, directly applying GAN is problematic because GAN focuses on only the positive data. The resulting PU learning method will have high precision but low recall. We propose a new objective function based on KLdivergence. Evaluation using both image and text data shows that PAN outperforms state-of-the-art PU learning methods and also a direct adaptation of GAN for PU learning.

PDF Details

AAAI Conference 2021 Conference Paper

Reinforced History Backtracking for Conversational Question Answering

  • Minghui Qiu
  • Xinjing Huang
  • Cen Chen
  • Feng Ji
  • Chen Qu
  • Wei Wei
  • Jun Huang
  • Yin Zhang

To model the context history in multi-turn conversations has become a critical step towards a better understanding of the user query in question answering systems. To utilize the context history, most existing studies treat the whole context as input, which will inevitably face the following two challenges. First, modeling a long history can be costly as it requires more computation resources. Second, the long context history consists of a lot of irrelevant information that makes it difficult to model appropriate information relevant to the user query. To alleviate these problems, we propose a reinforcement learning based method to capture and backtrack the related conversation history to boost model performance in this paper. Our method seeks to automatically backtrack the history information with the implicit feedback from the model performance. We further consider both immediate and delayed rewards to guide the reinforced backtracking policy. Extensive experiments on a large conversational question answering dataset show that the proposed method can help to alleviate the problems arising from longer context history. Meanwhile, experiments show that the method yields better performance than other strong baselines, and the actions made by the method are insightful.

PDF Details

AAAI Conference 2020 Conference Paper

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

  • 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. In this paper, we propose a novel method to acquire a satisfying policy and subtly circumvent the knotty dialogue state representation problem in the multi-domain setting. Inspired by real school teaching scenarios, our method is composed of multiple domain-specific teachers and a universal student. Each individual teacher only focuses on one specific domain and learns its corresponding domain knowledge and dialogue policy based on a precisely extracted single domain dialogue state representation. Then, these domainspecific teachers impart their domain knowledge and policies to a universal student model and collectively make this student model a multi-domain dialogue expert. Experiment results show that our method reaches competitive results with SOTAs in both multi-domain and single domain setting.

PDF Details