arXiv subjects

Zhewei Wei

Publications and source records attributed to Zhewei Wei.

At least 37 records · Page 2Linked to original sources

arXiv2026

GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation

Large language models (LLMs) have shown promise in simulating human-like social behaviors. Social graphs provide high-quality supervision signals that encode both local interactions and global network structure, yet they remain underutilized for LLM training. To address this gap, we propose Graphia, the first general LLM-based social graph simulation framework that leverages graph data as supervision for LLM post-training via reinforcement learning. With GNN-based structural rewards, Graphia trains specialized agents to predict whom to interact with (destination selection) and how to interact (edge generation), followed by designed graph generation pipelines. We evaluate Graphia under two settings: Transductive Dynamic Graph Generation (TDGG), a micro-level task with our proposed node-wise interaction alignment metrics; and Inductive Dynamic Graph Generation (IDGG), a macro-level task with our proposed metrics for aligning emergent network properties. On three real-world networks, Graphia improves micro-level alignment by 6.1% in the composite destination selection score, 12% in edge classification accuracy, and 27.9% in edge content BERTScore over the strongest baseline. For macro-level alignment, it achieves 35.98% higher structural similarity and 28.71% better replication of social phenomena such as power laws and echo chambers. Our results show that social graphs can serve as high-quality supervision signals for LLM post-training, closing the gap between agent behaviors and network dynamics for LLM-based simulation. Code is available at https://github.com/Ji-Cather/Graphia.git.

cs.SI↗

arXiv2026

Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching

Linear bandits have become a cornerstone of online learning and sequential decision-making, providing solid theoretical foundations for balancing exploration and exploitation. Within this domain, matrix sketching serves as a critical component for achieving computational efficiency, especially when confronting high-dimensional problem instances. The sketch-based approaches reduce per-round complexity from $Ω(d^2)$ to $O(dl)$, where $d$ is the dimension and $l<d$ is the sketch size. However, this computational efficiency comes with a fundamental pitfall: when the streaming matrix exhibits heavy spectral tails, such algorithms can incur vacuous \textit{linear regret}. In this paper, we revisit the regret bounds and algorithmic design for sketch-based linear bandits. Our analysis reveals that inappropriate sketch sizes can lead to substantial spectral error, severely undermining regret guarantees. To overcome this issue, we propose Dyadic Block Sketching, a novel multi-scale matrix sketching approach that dynamically adjusts the sketch size during the learning process. We apply this technique to linear bandits and demonstrate that the new algorithm achieves \textit{sublinear regret} bounds without requiring prior knowledge of the streaming matrix properties. It establishes a general framework for efficient sketch-based linear bandits, which can be integrated with any matrix sketching method that provides covariance guarantees. Comprehensive experimental evaluation demonstrates the superior utility-efficiency trade-off achieved by our approach.

cs.LG↗

arXiv2026

GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning

Dynamic Text-Attributed Graphs (DyTAGs), which intricately integrate structural, temporal, and textual attributes, are crucial for modeling complex real-world systems. However, most existing DyTAG datasets exhibit poor textual quality, which severely limits their utility for generative DyTAG tasks requiring semantically rich inputs. Additionally, prior work mainly focuses on discriminative tasks on DyTAGs, resulting in a lack of standardized task formulations and evaluation protocols tailored for DyTAG generation. To address these critical issues, we propose Generative DyTAG Benchmark (GDGB), which comprises eight meticulously curated DyTAG datasets with high-quality textual features for both nodes and edges, overcoming limitations of prior datasets. Building on GDGB, we define two novel DyTAG generation tasks: Transductive Dynamic Graph Generation (TDGG) and Inductive Dynamic Graph Generation (IDGG). TDGG transductively generates a target DyTAG based on the given source and destination node sets, while the more challenging IDGG introduces new node generation to inductively model the dynamic expansion of real-world graph data. To enable holistic evaluation, we design multifaceted metrics that assess the structural, temporal, and textual quality of the generated DyTAGs. We further propose GAG-General, an LLM-based multi-agent generative framework tailored for reproducible and robust benchmarking of DyTAG generation. Experimental results demonstrate that GDGB enables rigorous evaluation of TDGG and IDGG, with key insights revealing the critical interplay of structural and textual features in DyTAG generation. These findings establish GDGB as a foundational resource for advancing generative DyTAG research and unlocking further practical applications in DyTAG generation. The dataset and source code are available at https://github.com/Lucas-PJ/GDGB-ALGO.

cs.AI↗

arXiv2026

On Solving Asymmetric Diagonally Dominant Linear Systems in Sublinear Time

We initiate a study of solving a row/column diagonally dominant (RDD/CDD) linear system $Mx=b$ in sublinear time, with the goal of estimating $t^{\top}x^*$ for a given vector $t\in R^n$ and a specific solution $x^*$. This setting naturally generalizes the study of sublinear-time solvers for symmetric diagonally dominant (SDD) systems [AKP19] to the asymmetric case. Our first contributions are characterizations of the problem's mathematical structure. We express a solution $x^*$ via a Neumann series, prove its convergence, and upper bound the truncation error on this series through a novel quantity of $M$, termed the maximum $p$-norm gap. This quantity generalizes the spectral gap of symmetric matrices and captures how the structure of $M$ governs the problem's computational difficulty. For systems with bounded maximum $p$-norm gap, we develop a collection of algorithmic results for locally approximating $t^{\top}x^*$ under various scenarios and error measures. We derive these results by adapting the techniques of random-walk sampling, local push, and their bidirectional combination, which have proved powerful for special cases of solving RDD/CDD systems, particularly estimating PageRank and effective resistance on graphs. Our general framework yields deeper insights, extended results, and improved complexity bounds for these problems. Notably, our perspective provides a unified understanding of Forward Push and Backward Push, two fundamental approaches for estimating random-walk probabilities on graphs. Our framework also inherits the hardness results for sublinear-time SDD solvers and local PageRank computation, establishing lower bounds on the maximum $p$-norm gap or the accuracy parameter. We hope that our work opens the door for further study into sublinear solvers, local graph algorithms, and directed spectral graph theory.

cs.DS↗

arXiv2026

AeroSketch: Near-Optimal Time Matrix Sketch Framework for Persistent, Sliding Window, and Distributed Streams

Many real-world matrix datasets arrive as high-throughput vector streams, making it impractical to store or process them in their entirety. To enable real-time analytics under limited computational, memory, and communication resources, matrix sketching techniques have been developed over recent decades to provide compact approximations of such streaming data. Some algorithms have achieved optimal space and communication complexity. However, these approaches often require frequent time-consuming matrix factorization operations. In particular, under tight approximation error bounds, each matrix factorization computation incurs cubic time complexity, thereby limiting their update efficiency. In this paper, we introduce AeroSketch, a novel matrix sketching framework that leverages recent advances in randomized numerical linear algebra (RandNLA). AeroSketch achieves optimal communication and space costs while delivering near-optimal update time complexity (within logarithmic factors) across persistent, sliding window, and distributed streaming scenarios. Extensive experiments on both synthetic and real-world datasets demonstrate that AeroSketch consistently outperforms state-of-the-art methods in update throughput. In particular, under tight approximation error constraints, AeroSketch reduces the cubic time complexity to the quadratic level. Meanwhile, it maintains comparable approximation quality while retaining optimal communication and space costs.

cs.DB↗

arXiv2026

PageRank Centrality in Directed Graphs with Bounded In-Degree

We study the computational complexity of locally estimating a node's PageRank centrality in a directed graph $G$. For any node $t$, its PageRank centrality $π(t)$ is defined as the probability that a random walk in $G$, starting from a uniformly chosen node, terminates at $t$, where each step terminates with a constant probability $α\in(0,1)$. To obtain a multiplicative $\big(1\pm O(1)\big)$-approximation of $π(t)$ with probability $Ω(1)$, the previously best upper bound is $O(n^{1/2}\min\{ Δ_{in}^{1/2},Δ_{out}^{1/2},m^{1/4}\})$ from [Wang, Wei, Wen, Yang, STOC '24], where $n$ and $m$ denote the number of nodes and edges in $G$, and $Δ_{in}$ and $Δ_{out}$ upper bound the in-degrees and out-degrees of $G$, respectively. Using a refinement of the proof in the same paper, we establish a lower bound of $Ω(n^{1/2}\min\{Δ_{in}^{1/2}/n^γ,Δ_{out}^{1/2}/n^γ,m^{1/4}\})$, where $γ=\frac{1}{2}(2\max\{\log_{1/(1-α)}Δ_{in},1\}-1)^{-1}$. As $γ$ only depends on $Δ_{in}$ and $n^γ=O(1)$ for $Δ_{in}=Ω\left(n^{Ω(1)}\right)$, the known upper bound is tight if we only parameterize the complexity by $n$, $m$, and $Δ_{out}$. However, there remains a gap of $Ω(n^γ)$ when considering $Δ_{in}$, and this gap is large when $Δ_{in}$ is small. In the extreme case where $Δ_{in}\le1/(1-α)$, we have $γ=1/2$, leading to a gap of $Ω(n^{1/2})$ between the bounds $O(n^{1/2})$ and $Ω(1)$. In this paper, we present a new algorithm that achieves the above lower bound (up to logarithmic factors). The algorithm assumes that $n$ and the bounds $Δ_{in}$ and $Δ_{out}$ are known in advance. Our key technique is a novel randomized backwards propagation process that only propagates selectively based on Monte Carlo estimated PageRank scores.

cs.DS↗

arXiv2025

Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents

Recent research has explored the use of Large Language Models (LLMs) for tackling complex graph reasoning tasks. However, due to the intricacies of graph structures and the inherent limitations of LLMs in handling long text, current approaches often fail to deliver satisfactory accuracy, even on small-scale graphs and simple tasks. To address these challenges, we introduce GraphAgent-Reasoner, a fine-tuning-free framework that utilizes a multi-agent collaboration strategy for explicit and precise graph reasoning. Inspired by distributed graph computation theory, our framework decomposes graph problems into smaller, node-centric tasks that are distributed among multiple agents. The agents collaborate to solve the overall problem, significantly reducing the amount of information and complexity handled by a single LLM, thus enhancing the accuracy of graph reasoning. By simply increasing the number of agents, GraphAgent-Reasoner can efficiently scale to accommodate larger graphs with over 1,000 nodes. Evaluated on the GraphInstruct dataset, our framework demonstrates near-perfect accuracy on polynomial-time graph reasoning tasks, significantly outperforming the best available models, both closed-source and fine-tuned open-source variants. Our framework also demonstrates the capability to handle real-world graph reasoning applications such as webpage importance analysis.

cs.AI↗

arXiv2025

Leveraging LLM-based agents for social science research: insights from citation network simulations

The emergence of Large Language Models (LLMs) demonstrates their potential to encapsulate the logic and patterns inherent in human behavior simulation by leveraging extensive web data pre-training. However, the boundaries of LLM capabilities in social simulation remain unclear. To further explore the social attributes of LLMs, we introduce the CiteAgent framework, designed to generate citation networks based on human-behavior simulation with LLM-based agents. CiteAgent successfully captures predominant phenomena in real-world citation networks, including power-law distribution, citational distortion, and shrinking diameter. Building on this realistic simulation, we establish two LLM-based research paradigms in social science: LLM-SE (LLM-based Survey Experiment) and LLM-LE (LLM-based Laboratory Experiment). These paradigms facilitate rigorous analyses of citation network phenomena, allowing us to validate and challenge existing theories. Additionally, we extend the research scope of traditional science of science studies through idealized social experiments, with the simulation experiment results providing valuable insights for real-world academic environments. Our work demonstrates the potential of LLMs for advancing science of science research in social science.

physics.soc-ph↗

arXiv2025

Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses

While Graph Neural Networks (GNNs) and Large Language Models (LLMs) are powerful approaches for learning on Text-Attributed Graphs (TAGs), a comprehensive understanding of their robustness remains elusive. Current evaluations are fragmented, failing to systematically investigate the distinct effects of textual and structural perturbations across diverse models and attack scenarios. To address these limitations, we introduce a unified and comprehensive framework to evaluate robustness in TAG learning. Our framework evaluates classical GNNs, robust GNNs (RGNNs), and GraphLLMs across ten datasets from four domains, under diverse text-based, structure-based, and hybrid perturbations in both poisoning and evasion scenarios. Our extensive analysis reveals multiple findings, among which three are particularly noteworthy: 1) models have inherent robustness trade-offs between text and structure, 2) the performance of GNNs and RGNNs depends heavily on the text encoder and attack type, and 3) GraphLLMs are particularly vulnerable to training data corruption. To overcome the identified trade-offs, we introduce SFT-auto, a novel framework that delivers superior and balanced robustness against both textual and structural attacks within a single model. Our work establishes a foundation for future research on TAG security and offers practical solutions for robust TAG learning in adversarial environments. Our code is available at: https://github.com/Leirunlin/TGRB.

cs.LG↗

arXiv2025

Lighter-X: An Efficient and Plug-and-play Strategy for Graph-based Recommendation through Decoupled Propagation

Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness in recommendation systems. However, conventional graph-based recommenders, such as LightGCN, require maintaining embeddings of size $d$ for each node, resulting in a parameter complexity of $\mathcal{O}(n \times d)$, where $n$ represents the total number of users and items. This scaling pattern poses significant challenges for deployment on large-scale graphs encountered in real-world applications. To address this scalability limitation, we propose \textbf{Lighter-X}, an efficient and modular framework that can be seamlessly integrated with existing GNN-based recommender architectures. Our approach substantially reduces both parameter size and computational complexity while preserving the theoretical guarantees and empirical performance of the base models, thereby enabling practical deployment at scale. Specifically, we analyze the original structure and inherent redundancy in their parameters, identifying opportunities for optimization. Based on this insight, we propose an efficient compression scheme for the sparse adjacency structure and high-dimensional embedding matrices, achieving a parameter complexity of $\mathcal{O}(h \times d)$, where $h \ll n$. Furthermore, the model is optimized through a decoupled framework, reducing computational complexity during the training process and enhancing scalability. Extensive experiments demonstrate that Lighter-X achieves comparable performance to baseline models with significantly fewer parameters. In particular, on large-scale interaction graphs with millions of edges, we are able to attain even better results with only 1\% of the parameter over LightGCN.

cs.LG↗

arXiv2025

Rethinking and Benchmarking Large Language Models for Graph Reasoning

Large Language Models (LLMs) for Graph Reasoning have been extensively studied over the past two years, involving enabling LLMs to understand graph structures and reason on graphs to solve various graph problems, with graph algorithm problems being the most prevalent. Recent studies underscore the potential of LLMs in handling graph reasoning tasks, but their performance is underwhelming. In this work, we point out issues with existing methods and benchmarks, and rethink the direction that LLMs for graph reasoning should strive toward. We find that base models, e.g., GPT-4o-mini, are largely underestimated due to improper reasoning focus. Base models with reasoning focus redirected from replicating graph algorithms to designing them can easily solve most graph reasoning tasks in existing benchmarks. To truly evaluate the graph reasoning capabilities of LLMs, we construct a more challenging GraphAlgorithm benchmark, comprising 239 different graph problems and 3,041 test instances collected from 4 competition platforms. Finally, we introduce a simple and strong baseline Simple-Reasoning-Then-Coding (Simple-RTC)-which guides LLMs to design graph algorithms first and then code to address graph reasoning tasks. Simple-RTC achieves near-perfect accuracy on existing benchmarks and significantly outperforms GPT-4o-mini and all prior methods on the GraphAlgorithm benchmark. This strong baseline encourages further advancements in LLMs for Graph Reasoning in the future.

cs.AI↗

arXiv2025

Fast Second-Order Online Kernel Learning through Incremental Matrix Sketching and Decomposition

Online Kernel Learning (OKL) has attracted considerable research interest due to its promising predictive performance in streaming environments. Second-order approaches are particularly appealing for OKL as they often offer substantial improvements in regret guarantees. However, existing second-order OKL approaches suffer from at least quadratic time complexity with respect to the pre-set budget, rendering them unsuitable for meeting the real-time demands of large-scale streaming recommender systems. The singular value decomposition required to obtain explicit feature mapping is also computationally expensive due to the complete decomposition process. Moreover, the absence of incremental updates to manage approximate kernel space causes these algorithms to perform poorly in adversarial environments and real-world streaming recommendation datasets. To address these issues, we propose FORKS, a fast incremental matrix sketching and decomposition approach tailored for second-order OKL. FORKS constructs an incremental maintenance paradigm for second-order kernelized gradient descent, which includes incremental matrix sketching for kernel approximation and incremental matrix decomposition for explicit feature mapping construction. Theoretical analysis demonstrates that FORKS achieves a logarithmic regret guarantee on par with other second-order approaches while maintaining a linear time complexity w.r.t. the budget, significantly enhancing efficiency over existing approaches. We validate the performance of FORKS through extensive experiments conducted on real-world streaming recommendation datasets, demonstrating its superior scalability and robustness against adversarial attacks.

cs.LG↗

arXiv2025

A Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications

Geometric graphs are a special kind of graph with geometric features, which are vital to model many scientific problems. Unlike generic graphs, geometric graphs often exhibit physical symmetries of translations, rotations, and reflections, making them ineffectively processed by current Graph Neural Networks (GNNs). To address this issue, researchers proposed a variety of geometric GNNs equipped with invariant/equivariant properties to better characterize the geometry and topology of geometric graphs. Given the current progress in this field, it is imperative to conduct a comprehensive survey of data structures, models, and applications related to geometric GNNs. In this paper, based on the necessary but concise mathematical preliminaries, we formalize geometric graph as the data structure, on top of which we provide a unified view of existing models from the geometric message passing perspective. Additionally, we summarize the applications as well as the related datasets to facilitate later research for methodology development and experimental evaluation. We also discuss the challenges and future potential directions of geometric GNNs at the end of this survey.

cs.LG↗

arXiv2025

Future Link Prediction Without Memory or Aggregation

Future link prediction on temporal graphs is a fundamental task with wide applicability in real-world dynamic systems. These scenarios often involve both recurring (seen) and novel (unseen) interactions, requiring models to generalize effectively across both types of edges. However, existing methods typically rely on complex memory and aggregation modules, yet struggle to handle unseen edges. In this paper, we revisit the architecture of existing temporal graph models and identify two essential but overlooked modeling requirements for future link prediction: representing nodes with unique identifiers and performing target-aware matching between source and destination nodes. To this end, we propose Cross-Attention based Future Link Predictor on Temporal Graphs (CRAFT), a simple yet effective architecture that discards memory and aggregation modules and instead builds on two components: learnable node embeddings and cross-attention between the destination and the source's recent interactions. This design provides strong expressive power and enables target-aware modeling of the compatibility between candidate destinations and the source's interaction patterns. Extensive experiments on diverse datasets demonstrate that CRAFT consistently achieves superior performance with high efficiency, making it well-suited for large-scale real-world applications.

cs.LG↗

arXiv2025

Rethinking Link Prediction for Directed Graphs

Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising improvements. However, these methods often lack a thorough analysis of their expressiveness and suffer from effective benchmarks for a fair evaluation. In this paper, we propose a unified framework to assess the expressiveness of existing methods, highlighting the impact of dual embeddings and decoder design on directed link prediction performance. To address limitations in current benchmark setups, we introduce DirLinkBench, a robust new benchmark with comprehensive coverage, standardized evaluation, and modular extensibility. The results on DirLinkBench show that current methods struggle to achieve strong performance, while DiGAE outperforms other baselines overall. We further revisit DiGAE theoretically, showing its graph convolution aligns with GCN on an undirected bipartite graph. Inspired by these insights, we propose a novel Spectral Directed Graph Auto-Encoder SDGAE that achieves state-of-the-art average performance on DirLinkBench. Finally, we analyze key factors influencing directed link prediction and highlight open challenges in this field.

cs.LG↗

arXiv2025

Simple and Optimal Algorithms for Heavy Hitters and Frequency Moments in Distributed Models

We consider the problems of distributed heavy hitters and frequency moments in both the coordinator model and the distributed tracking model (also known as the distributed functional monitoring model). We present simple and optimal (up to logarithmic factors) algorithms for $\ell_p$ heavy hitters and $F_p$ estimation ($p \geq 2$) in these distributed models. For $\ell_p$ heavy hitters in the coordinator model, our algorithm requires only one round and uses $\tilde{O}(k^{p-1}/\eps^p)$ bits of communication. For $p > 2$, this is the first near-optimal result. By combining our algorithm with the standard recursive sketching technique, we obtain a near-optimal two-round algorithm for $F_p$ in the coordinator model, matching a significant result from recent work by Esfandiari et al.\ (STOC 2024). Our algorithm and analysis are much simpler and have better costs with respect to logarithmic factors. Furthermore, our technique provides a one-round algorithm for $F_p$, which is a significant improvement over a result of Woodruff and Zhang (STOC 2012). Thanks to the simplicity of our heavy hitter algorithms, we manage to adapt them to the distributed tracking model with only a $\polylog(n)$ increase in communication. For $\ell_p$ heavy hitters, our algorithm has a communication cost of $\tilde{O}(k^{p-1}/\eps^p)$, representing the first near-optimal algorithm for all $p \geq 2$. By applying the recursive sketching technique, we also provide the first near-optimal algorithm for $F_p$ in the distributed tracking model, with a communication cost of $\tilde{O}(k^{p-1}/\eps^2)$ for all $p \geq 2$. Even for $F_2$, our result improves upon the bounds established by Cormode, Muthukrishnan, and Yi (SODA 2008) and Woodruff and Zhang (STOC 2012), nearly matching the existing lower bound for the first time.

cs.DS↗

arXiv2025

Efficiency Unleashed: Inference Acceleration for LLM-based Recommender Systems with Speculative Decoding

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers, generating augmented knowledge for downstream tasks. However, in recommendation scenarios with numerous users and items, even offline knowledge generation with LLMs demands significant time and computational resources. This inefficiency arises from the autoregressive nature of LLMs. A promising solution is speculative decoding, a Draft-Then-Verify approach that increases the number of tokens generated per decoding step. In this work, we first identify recommendation knowledge generation as a highly fitting use case for retrieval-based speculative decoding. Then, we discern its two characteristics: (1) the vast number of items and users in RSs leads to retrieval inefficiency, and (2) RSs exhibit high diversity tolerance for LLM-generated text. Building on these insights, we introduce Lossless Acceleration via Speculative Decoding for LLM-based Recommender Systems (LASER), which features a Customized Retrieval Pool to enhance retrieval efficiency and Relaxed Verification to improve the acceptance rate of draft tokens. LASER achieves a 3-5x speedup on public datasets and saves about 67\% of computational resources during the online A/B test on a large-scale advertising scenario with lossless downstream recommendation performance. Our code is available at https://github.com/YunjiaXi/LASER

cs.IR↗

arXiv2025

TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics

Future link prediction is a fundamental challenge in various real-world dynamic systems. To address this, numerous temporal graph neural networks (temporal GNNs) and benchmark datasets have been developed. However, these datasets often feature excessive repeated edges and lack complex sequential dynamics, a key characteristic inherent in many real-world applications such as recommender systems and ``Who-To-Follow'' on social networks. This oversight has led existing methods to inadvertently downplay the importance of learning sequential dynamics, focusing primarily on predicting repeated edges. In this study, we demonstrate that existing methods, such as GraphMixer and DyGFormer, are inherently incapable of learning simple sequential dynamics, such as ``a user who has followed OpenAI and Anthropic is more likely to follow AI at Meta next.'' Motivated by this issue, we introduce the Temporal Graph Benchmark with Sequential Dynamics (TGB-Seq), a new benchmark carefully curated to minimize repeated edges, challenging models to learn sequential dynamics and generalize to unseen edges. TGB-Seq comprises large real-world datasets spanning diverse domains, including e-commerce interactions, movie ratings, business reviews, social networks, citation networks and web link networks. Benchmarking experiments reveal that current methods usually suffer significant performance degradation and incur substantial training costs on TGB-Seq, posing new challenges and opportunities for future research. TGB-Seq datasets, leaderboards, and example codes are available at https://tgb-seq.github.io/.

cs.LG↗