arXiv subjects

Feng Ji

Publications and source records attributed to Feng Ji.

At least 55 records · Page 3Linked to original sources

arXiv2024

Generalized Graph Signal Reconstruction via the Uncertainty Principle

We introduce a novel uncertainty principle for generalized graph signals that extends classical time-frequency and graph uncertainty principles into a unified framework. By defining joint vertex-time and spectral-frequency spreads, we quantify signal localization across these domains, revealing a trade-off between them. This framework allows us to identify a class of signals with maximal energy concentration in both domains, forming the fundamental atoms for a new joint vertex-time dictionary. This dictionary enhances signal reconstruction under practical constraints, such as incomplete or intermittent data, commonly encountered in sensor and social networks. Numerical experiments on real-world datasets demonstrate the effectiveness of the proposed approach, showing improved reconstruction accuracy and noise robustness compared to existing methods.

eess.SP↗

arXiv2024

Spectral Convergence of Complexon Shift Operators

Topological Signal Processing (TSP) utilizes simplicial complexes to model structures with higher order than vertices and edges. In this paper, we study the transferability of TSP via a generalized higher-order version of graphon, known as complexon. We recall the notion of a complexon as the limit of a simplicial complex sequence [1]. Inspired by the graphon shift operator and message-passing neural network, we construct a marginal complexon and complexon shift operator (CSO) according to components of all possible dimensions from the complexon. We investigate the CSO's eigenvalues and eigenvectors and relate them to a new family of weighted adjacency matrices. We prove that when a simplicial complex signal sequence converges to a complexon signal, the eigenvalues, eigenspaces, and Fourier transform of the corresponding CSOs converge to that of the limit complexon signal. This conclusion is further verified by two numerical experiments. These results hint at learning transferability on large simplicial complexes or simplicial complex sequences, which generalize the graphon signal processing framework.

eess.SP↗

arXiv2024

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

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}.

cs.LG↗

arXiv2024

A sampling construction of graphon 1-norm convergence

In the short note, we describe a sampling construction that yields a sequence of graphons converging to a prescribed limit graphon in 1-norm. This convergence is stronger than the convergence in the cut norm, usually used to study graphon sequences. The note also contains errata of the previous version of the note.

eess.SP↗

arXiv2024

Modeling Sparse Graph Sequences and Signals Using Generalized Graphons

Graphons are limit objects of sequences of graphs and are used to analyze the behavior of large graphs. Recently, graphon signal processing has been developed to study signal processing on large graphs. A major limitation of this approach is that any sparse sequence of graphs inevitably converges to the zero graphon, rendering the resulting signal processing theory trivial and inadequate for sparse graph sequences. To overcome this limitation, we propose a new signal processing framework that leverages the concept of generalized graphons and introduces the stretched cut distance as a measure to compare these graphons. Our framework focuses on the sampling of graph sequences from generalized graphons and explores the convergence properties of associated operators, spectra, and signals. Our signal processing framework provides a comprehensive approach to analyzing and processing signals on graph sequences, even if they are sparse. Finally, we discuss the practical implications of our theory for real-world large networks through numerical experiments.

eess.SP↗

arXiv2024

Online Signed Sampling of Bandlimited Graph Signals

The theory of sampling and recovery of bandlimited graph signals has been extensively studied. However, in many cases, the observation of a signal is quite coarse. For example, users only provide simple comments such as "like" or "dislike" for a product on an e-commerce platform. This is a particular scenario where only the sign information of a graph signal can be measured. In this paper, we are interested in how to sample based on sign information in an online manner, by which the direction of the original graph signal can be estimated. The online signed sampling problem of a graph signal can be formulated as a Markov decision process in a finite horizon. Unfortunately, it is intractable for large size graphs. We propose a low-complexity greedy signed sampling algorithm (GSS) as well as a stopping criterion. Meanwhile, we prove that the objective function is adaptive monotonic and adaptive submodular, so that the performance is close enough to the global optimum with a lower bound. Finally, we demonstrate the effectiveness of the GSS algorithm by both synthesis and realworld data.

eess.SP↗

arXiv2024

Graph Neural Networks with a Distribution of Parametrized Graphs

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. We obtain the maximum likelihood estimate of the network parameters in an Expectation-Maximization (EM) framework based on the multiple graphs. 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 heterogeneous graphs and graph regression on chemistry datasets.

cs.LG↗

arXiv2024

Node Flux-Linkage Synchronizing Control of Power Systems with 100% Wind Power Generation Based on Capacitor Voltage Balancing Scheme

This paper proposes a node flux-linkage synchronizing control method (NFSCM) for power systems with 100% wind power generation based on a capacitor voltage balancing scheme (CVBS). Different from the conventional grid-forming controllers, NFSCM is designed to regulate inverters as virtual flux-linkage sources. Auto-synchronization of flux-linkage vectors is achieved through the CVBS-based NFSCM. The mismatch among the angular frequencies of flux-linkage vectors is eliminated by regulating the tracking errors of DC-link voltages, which establishes a negative feedback between the output frequency and active power of the inverter. NFSCM is adaptive to weak and strong grids. It avoids the excitation inrush currents in the step-up transformer of wind power generators. It also eliminates the DC components of the three-phase currents, and avoids low-frequency oscillations in active power. In order to limit the short-circuit current of inverters, a logic-based bang-bang funnel control (LBFC) is designed to control the switches of inverter bridges when over-current is detected. LBFC is able to restrict various fault currents within an acceptable range within the shortest time. LBFC and NFSCM are designed to operate in a switched manner according to a state-dependent switching strategy. Time-domain simulations were conducted on a 100% wind power generation test system, and the performance of NFSCM and LBFC were investigated.

eess.SY↗

arXiv2024

Lagrangian Modelling and Motion Stability of Synchronous Generator Power Systems

This paper proposes to analyze the motion stability of synchro-nous generator power systems using a Lagrangian model derived in the configuration space of generalized position and speed. In the first place, a Lagrangian model of synchronous generators is derived based on Lagrangian mechanics. The generalized potential energy of inductors and generalized kinetic energy of capacitors are defined. The mechanical and electrical dynamics can be modelled in a unified manner through constructing a Lagrangian function. Taking the first benchmark model of subsynchronous oscillation as an example, a Lagragian model is construct-ed and numerical solution of the model is obtained to validate the accuracy and effectiveness of the model. Compared with the traditional EMTP model in PSCAD, the obtained Lagrangian model is able to accurately describe the electromagnetic transient process of the system. Moreover, the Lagrangian model is analytical, which enables to analyze the motion stability of the system using Lyapunov motion stability theory. The Lagrangian model can not only be used to discuss the power angle stability, but also used for analyzing the stability of node voltages and frequency. It provides the feasibility for studying the unified stability of power systems.

eess.SY↗

arXiv2023

Lossless digraph signal processing via polar decomposition

In this paper, we present a signal processing framework for directed graphs. Unlike undirected graphs, a graph shift operator such as the adjacency matrix associated with a directed graph usually does not admit an orthogonal eigenbasis. This makes it challenging to define the Fourier transform. Our methodology leverages the polar decomposition to define two distinct eigendecompositions, each associated with different matrices derived from this decomposition. We propose to extend the frequency domain and introduce a Fourier transform that jointly encodes the spectral response of a signal for the two eigenbases from the polar decomposition. This allows us to define convolution following a standard routine. Our approach has two features: it is lossless as the shift operator can be fully recovered from factors of the polar decomposition. Moreover, it subsumes the traditional graph signal processing if the graph is directed. We present numerical results to show how the framework can be applied.

eess.SP↗

arXiv2023

Generalized signals on simplicial complexes

Topological signal processing (TSP) over simplicial complexes typically assumes observations associated with the simplicial complexes are real scalars. In this paper, we develop TSP theories for the case where observations belong to general abelian groups, including function spaces that are commonly used to represent time-varying signals. Our approach generalizes the Hodge decomposition and allows for signal processing tasks to be performed on these more complex observations. We propose a unified and flexible framework for TSP that expands its applicability to a wider range of signal processing applications. Numerical results demonstrate the effectiveness of this approach and provide a foundation for future research in this area.

eess.SP↗

arXiv2023

FRGNN: Mitigating the Impact of Distribution Shift on Graph Neural Networks via Test-Time Feature Reconstruction

Due to inappropriate sample selection and limited training data, a distribution shift often exists between the training and test sets. This shift can adversely affect the test performance of Graph Neural Networks (GNNs). Existing approaches mitigate this issue by either enhancing the robustness of GNNs to distribution shift or reducing the shift itself. However, both approaches necessitate retraining the model, which becomes unfeasible when the model structure and parameters are inaccessible. To address this challenge, we propose FR-GNN, a general framework for GNNs to conduct feature reconstruction. FRGNN constructs a mapping relationship between the output and input of a well-trained GNN to obtain class representative embeddings and then uses these embeddings to reconstruct the features of labeled nodes. These reconstructed features are then incorporated into the message passing mechanism of GNNs to influence the predictions of unlabeled nodes at test time. Notably, the reconstructed node features can be directly utilized for testing the well-trained model, effectively reducing the distribution shift and leading to improved test performance. This remarkable achievement is attained without any modifications to the model structure or parameters. We provide theoretical guarantees for the effectiveness of our framework. Furthermore, we conduct comprehensive experiments on various public datasets. The experimental results demonstrate the superior performance of FRGNN in comparison to multiple categories of baseline methods.

cs.LG↗

arXiv2023

Generalized Graphon Process: Convergence of Graph Frequencies in Stretched Cut Distance

Graphons have traditionally served as limit objects for dense graph sequences, with the cut distance serving as the metric for convergence. However, sparse graph sequences converge to the trivial graphon under the conventional definition of cut distance, which make this framework inadequate for many practical applications. In this paper, we utilize the concepts of generalized graphons and stretched cut distance to describe the convergence of sparse graph sequences. Specifically, we consider a random graph process generated from a generalized graphon. This random graph process converges to the generalized graphon in stretched cut distance. We use this random graph process to model the growing sparse graph, and prove the convergence of the adjacency matrices' eigenvalues. We supplement our findings with experimental validation. Our results indicate the possibility of transfer learning between sparse graphs.

eess.SP↗

arXiv2023

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

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. We discuss their relations and differences. Toward the end, we provide an opinion on whether there is a consistent approach to convolution that unifies seemingly different approaches by different theories.

eess.SP↗

arXiv2023

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

Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. 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. We first introduce an adaptive learning strategy and teacher importance weight, which enables a student to effectively learn from max-margin teachers and easily adapt to new languages. Moreover, we present a shared student encoder with different projection layers in support of multiple languages, which contributes to largely reducing development and machine cost. Experimental results show that AMTSS gains competitive results on the public XNLI dataset and the realistic industrial dataset AliExpress (AE) in the E-commerce scenario.

cs.CL↗

arXiv2023

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

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.

cs.LG↗

arXiv2023

Effective Numerical Simulations of Synchronous Generator System

Synchronous generator system is a complicated dynamical system for energy transmission, which plays an important role in modern industrial production. In this article, we propose some predictor-corrector methods and structure-preserving methods for a generator system based on the first benchmark model of subsynchronous resonance, among which the structure-preserving methods preserve a Dirac structure associated with the so-called port-Hamiltonian descriptor systems. To illustrate this, the simplified generator system in the form of index-1 differential-algebraic equations has been derived. Our analyses provide the global error estimates for a special class of structure-preserving methods called Gauss methods, which guarantee their superior performance over the PSCAD/EMTDC and the predictor-corrector methods in terms of computational stability. Numerical simulations are implemented to verify the effectiveness and advantages of our methods.

math.NA↗

arXiv2023

Distributional Signals for Node Classification in Graph Neural Networks

In graph neural networks (GNNs), both node features and labels are examples of graph signals, a key notion in graph signal processing (GSP). While it is common in GSP to impose signal smoothness constraints in learning and estimation tasks, it is unclear how this can be done for discrete node labels. We bridge this gap by introducing the concept of distributional graph signals. In our framework, we work with the distributions of node labels instead of their values and propose notions of smoothness and non-uniformity of such distributional graph signals. We then propose a general regularization method for GNNs that allows us to encode distributional smoothness and non-uniformity of the model output in semi-supervised node classification tasks. Numerical experiments demonstrate that our method can significantly improve the performance of most base GNN models in different problem settings.

eess.SP↗