More Like this

1. Graph Neural Networks Are More Than Filters: Revisiting and Benchmarking from A Spectral Perspective

   Dong, Yushun; Soga, Patrick; He, Yinhan; Wang, Song; Li, Jundong (April 2025, International Conference on Learning Representations)

   Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based learning tasks. While their performance is often attributed to the powerful neighborhood aggregation mechanism, recent studies suggest that other components such as non-linear layers may also significantly affecting how GNNs process the input graph data in the spectral domain. Such evidence challenges the prevalent opinion that neighborhood aggregation mechanisms dominate the behavioral characteristics of GNNs in the spectral domain. To demystify such a conflict, this paper introduces a comprehensive benchmark to measure and evaluate GNNs' capability in capturing and leveraging the information encoded in different frequency components of the input graph data. Specifically, we first conduct an exploratory study demonstrating that GNNs can flexibly yield outputs with diverse frequency components even when certain frequencies are absent or filtered out from the input graph data. We then formulate a novel research problem of measuring and benchmarking the performance of GNNs from a spectral perspective. To take an initial step towards a comprehensive benchmark, we design an evaluation protocol supported by comprehensive theoretical analysis. Finally, we introduce a comprehensive benchmark on real-world datasets, revealing insights that challenge prevalent opinions from a spectral perspective. We believe that our findings will open new avenues for future advancements in this area. 

   more » « less
2. MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deployment

   https://doi.org/10.1145/3609386  

   Odema, Mohanad; Bouzidi, Halima; Ouarnoughi, Hamza; Niar, Smail; Al Faruque, Mohammad Abdullah (October 2023, ACM Transactions on Embedded Computing Systems)

   Graph Neural Networks (GNNs) are becoming increasingly popular for vision-based applications due to their intrinsic capacity in modeling structural and contextual relations between various parts of an image frame. On another front, the rising popularity of deep vision-based applications at the edge has been facilitated by the recent advancements in heterogeneous multi-processor Systems on Chips (MPSoCs) that enable inference under real-time, stringent execution requirements. By extension, GNNs employed for vision-based applications must adhere to the same execution requirements. Yet contrary to typical deep neural networks, the irregular flow of graph learning operations poses a challenge to running GNNs on such heterogeneous MPSoC platforms. In this paper, we propose a novel unifieddesign-mappingapproach for efficient processing of vision GNN workloads on heterogeneous MPSoC platforms. Particularly, we develop MaGNAS, a mapping-aware Graph Neural Architecture Search framework. MaGNAS proposes a GNN architectural design space coupled with prospective mapping options on a heterogeneous SoC to identify model architectures that maximize on-device resource efficiency. To achieve this, MaGNAS employs a two-tier evolutionary search to identify optimalGNNsandmappingpairings that yield the best performance trade-offs. Through designing a supernet derived from the recent Vision GNN (ViG) architecture, we conducted experiments on four (04) state-of-the-art vision datasets using both (i) a real hardware SoC platform (NVIDIA Xavier AGX) and (ii) a performance/cost model simulator for DNN accelerators. Our experimental results demonstrate that MaGNAS is able to provide1.57× latency speedup and is3.38× more energy-efficient for several vision datasets executed on the Xavier MPSoC vs. the GPU-only deployment while sustaining an average0.11%accuracy reduction from the baseline. 

   more » « less
3. Bayesian Graph Neural Networks with Adaptive Connection Sampling

   Hasanzadeh, Arman; Hajiramezanali, Ehsan; Boluki, Shahin; Zhou, Mingyuan; Duffield, Nick; Narayanan, Krishna; Qian, Xiaoning (January 2020, International Conference on Machine Learning)

   null (Ed.)

   We propose a unified framework for adap- tive connection sampling in graph neural net- works (GNNs) that generalizes existing stochas- tic regularization methods for training GNNs. The proposed framework not only alleviates over- smoothing and over-fitting tendencies of deep GNNs, but also enables learning with uncertainty in graph analytic tasks with GNNs. Instead of using fixed sampling rates or hand-tuning them as model hyperparameters as in existing stochas- tic regularization methods, our adaptive connec- tion sampling can be trained jointly with GNN model parameters in both global and local fash- ions. GNN training with adaptive connection sampling is shown to be mathematically equiv- alent to an efficient approximation of training Bayesian GNNs. Experimental results with abla- tion studies on benchmark datasets validate that adaptively learning the sampling rate given graph training data is the key to boosting the perfor- mance of GNNs in semi-supervised node classifi- cation, making them less prone to over-smoothing and over-fitting with more robust prediction. 

   more » « less
4. Graph Neural Networks for Charged Particle Tracking on FPGAs

   https://doi.org/10.3389/fdata.2022.828666  

   Elabd, Abdelrahman; Razavimaleki, Vesal; Huang, Shi-Yu; Duarte, Javier; Atkinson, Markus; DeZoort, Gage; Elmer, Peter; Hauck, Scott; Hu, Jin-Xuan; Hsu, Shih-Chieh; et al (March 2022, Frontiers in Big Data)

   The determination of charged particle trajectories in collisions at the CERN Large Hadron Collider (LHC) is an important but challenging problem, especially in the high interaction density conditions expected during the future high-luminosity phase of the LHC (HL-LHC). Graph neural networks (GNNs) are a type of geometric deep learning algorithm that has successfully been applied to this task by embedding tracker data as a graph—nodes represent hits, while edges represent possible track segments—and classifying the edges as true or fake track segments. However, their study in hardware- or software-based trigger applications has been limited due to their large computational cost. In this paper, we introduce an automated translation workflow, integrated into a broader tool called hls4ml , for converting GNNs into firmware for field-programmable gate arrays (FPGAs). We use this translation tool to implement GNNs for charged particle tracking, trained using the TrackML challenge dataset, on FPGAs with designs targeting different graph sizes, task complexites, and latency/throughput requirements. This work could enable the inclusion of charged particle tracking GNNs at the trigger level for HL-LHC experiments. 

   more » « less
5. Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment

   https://doi.org/10.1145/3616542  

   Zhao, Tianxiang; Luo, Dongsheng; Zhang, Xiang; Wang, Suhang (October 2023, ACM Transactions on Intelligent Systems and Technology)

   Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over recent years. Instance-level GNN explanation aims to discover critical input elements, such as nodes or edges, that the target GNN relies upon for making predictions. Though various algorithms are proposed, most of them formalize this task by searching the minimal subgraph, which can preserve original predictions. However, an inductive bias is deep-rooted in this framework: Several subgraphs can result in the same or similar outputs as the original graphs. Consequently, they have the danger of providing spurious explanations and failing to provide consistent explanations. Applying them to explain weakly performed GNNs would further amplify these issues. To address this problem, we theoretically examine the predictions of GNNs from the causality perspective. Two typical reasons for spurious explanations are identified: confounding effect of latent variables like distribution shift and causal factors distinct from the original input. Observing that both confounding effects and diverse causal rationales are encoded in internal representations,we propose a new explanation framework with an auxiliary alignment loss, which is theoretically proven to be optimizing a more faithful explanation objective intrinsically. Concretely for this alignment loss, a set of different perspectives are explored: anchor-based alignment, distributional alignment based on Gaussian mixture models, mutual-information-based alignment, and so on. A comprehensive study is conducted both on the effectiveness of this new framework in terms of explanation faithfulness/consistency and on the advantages of these variants. For our codes, please refer to the following URL link:https://github.com/TianxiangZhao/GraphNNExplanation 

   more » « less