We demonstrate ExGIS , a parallel inference query engine to support explainable Graph Neural Network (GNNs) inference analysis in large graphs. (1) For a class of GNNs ℳ L with at most L layers, and a graph G , ExGIS performs an offline, once-for-all compression of G to a small graph G c , such that for any inference query Q that requests the output of any GNN M ∈ ℳ L on any node v in G, G c can be directly queried to yield correct output without decompression. (2) Given a workload W of inference queries that requests the output of GNNs from ℳ over G , ExGIS perform fast online GNN inference and interpretation in parallel. It dynamically partitions W to balance workloads, and (a) executes inference that only consults compressed graph G c without decompression, and (b) directly yields concise, explanatory subgraphs from G c that can clarify the query output with high fidelity, all in parallel. Moreover, ExGIS integrates visual, interactive interfaces for query performance analysis, and a Large Language Models (LLMs)- enabled interpreter to support user-friendly, natural language explanation of query outputs. We demonstrate the compression rate and scalability of ExGIS, and its application in interpretable anomaly detection over bitcoin transaction networks and academic networks.

Graph Neural Networks (GNNs) have demonstrated promising performance in graph analysis. Nevertheless, the inference process of GNNs remains costly, hindering their applications for large graphs. This paper proposes inference-friendly graph compression (IFGC), a graph compression scheme to accelerate GNNs inference. Given a graph G and a GNN M , an IFGC computes a small compressed graph G c , to best preserve the inference results of M over G , such that the result can be directly inferred by accessing G c with no or little decompression cost. (1) We characterize IFGC with a class of inference equivalence relation. The relation captures the node pairs in G that are not distinguishable for GNN inference. (2) We introduce three practical specifications of IFGC for representative GNNs: structural preserving compression (SPGC), which computes G c that can be directly processed by GNN inference without decompression; ( α,r )-compression, that allows for a configurable trade-off between compression ratio and inference quality, and anchored compression that preserves inference results for specific nodes of interest. For each scheme, we introduce compression and inference algorithms with guarantees of efficiency and quality of the inferred results. We conduct extensive experiments on diverse sets of large-scale graphs, which verifies the effectiveness and efficiency of our graph compression approaches.

We demonstrate ModsNet , a search tool for pre-trained data science MOD el s recommendatio N using E xamplar da T aset. Given a set of pre-trained data science models, an "example" input dataset, and a user-specified performance metric, ModsNet answers the following query: "what are top-k models that have the best expected performance for the input data?" The need for searching high-quality pre-trained models is evident in data-driven analysis. Inspired by "query by example" paradigm, ModsNet does not require users to write complex queries, but only provide an "examplar" dataset, a task description, and a performance measure as input, and can automatically suggest top- k matching models that are expected to have desirable performance to perform the task over the provided sample dataset. ModsNet utilizes a knowledge graph to integrate model performances over datasets and synchronizes it with a bipartite graph neural network to estimate model performance, reduce inference cost, and promptly respond to top- k model search queries. To cope with strict cold-start (upon receiving a new dataset when no historical performance of registered models are observed), it performs a dynamic, cost-bounded "probe-and-select" strategy to incrementally identify promising models. We demonstrate the application of ModsNet in enabling efficient scientific data analysis.

Data analytical pipelines routinely involve various domain-specific data science models. Such models require expensive manual or training effort and often incur expensive validation costs (e.g., via scientific simulation analysis). Meanwhile, high-value models remain to be ad-hocly created, isolated, and underutilized for a broad community. Searching and accessing proper models for data analysis pipelines is desirable yet challenging for users without domain knowledge. This paper introduces ModsNet, a novel MODel SelectioN framework that only requires an Example daTaset. (1) We investigate the following problem: Given a library of pre-trained models, a limited amount of historical observations of their performance, and an "example" dataset as a query, return k models that are expected to perform the best over the query dataset. (2) We formulate a regression problem and introduce a knowledge-enhanced framework using a model-data interaction graph. Unlike traditional methods, (1) ModsNet uses a dynamic, cost-bounded "probe-and-select" strategy to incrementally identify promising pre-trained models in a strict cold-start scenario (when a new dataset without any interaction with existing models is given). (2) To reduce the learning cost, we develop a clustering-based sparsification strategy to prune unpromising models and their interactions. (3) We showcase of ModsNet built on top of a crowdsourced materials knowledge base platform. Our experiments verified its effectiveness, efficiency, and applications over real-world analytical pipelines.