Search

Shortcut learning refers to the phenomenon where models employ simple, non-robust decision rules in practical tasks, which hinders their generalization and robustness. With the rapid development of large language models (LLMs) in recent years, an increasing number of studies have shown the impact of shortcut learning on LLMs. This paper provides a novel perspective to review relevant research on shortcut learning in In-Context Learning (ICL). It conducts a detailed exploration of the types of shortcuts in ICL tasks, their causes, available benchmarks, and strategies for mitigating shortcuts. Based on corresponding observations, it summarizes the unresolved issues in existing research and attempts to outline the future research landscape of shortcut learning., Comment: 15 pages, 2 figures

Posterior sampling in contextual bandits with a Gaussian prior can be implemented exactly or approximately using the Laplace approximation. The Gaussian prior is computationally efficient but it cannot describe complex distributions. In this work, we propose approximate posterior sampling algorithms for contextual bandits with a diffusion model prior. The key idea is to sample from a chain of approximate conditional posteriors, one for each stage of the reverse process, which are estimated in a closed form using the Laplace approximation. Our approximations are motivated by posterior sampling with a Gaussian prior, and inherit its simplicity and efficiency. They are asymptotically consistent and perform well empirically on a variety of contextual bandit problems., Comment: Proceedings of the 38th Conference on Neural Information Processing Systems

In this paper, we introduce a new type of bionic AI that enhances decision-making unpredictability by incorporating responses from a living fly. Traditional AI systems, while reliable and predictable, lack nuanced and sometimes unseasoned decision-making seen in humans. Our approach uses a fly's varied reactions, to tune an AI agent in the game of Gobang. Through a study, we compare the performances of different strategies on altering AI agents and found a bionic AI agent to outperform human as well as conventional and white-noise enhanced AI agents. We contribute a new methodology for creating a bionic random function and strategies to enhance conventional AI agents ultimately improving unpredictability., Comment: iWOAR 2024 - 9th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These approaches commonly use a binary cross-entropy mechanism on pairwise samples, i.e., minimizing and maximizing the loss based on preferred or dis-preferred responses, respectively. However, while this training strategy omits the reward model, it also overlooks the varying preference degrees within different responses. We hypothesize that this is a key factor hindering LLMs from sufficiently understanding human preferences. To address this problem, we propose a novel Self-supervised Preference Optimization (SPO) framework, which constructs a self-supervised preference degree loss combined with the alignment loss, thereby helping LLMs improve their ability to understand the degree of preference. Extensive experiments are conducted on two widely used datasets of different tasks. The results demonstrate that SPO can be seamlessly integrated with existing preference optimization methods and significantly boost their performance to achieve state-of-the-art performance. We also conduct detailed analyses to offer comprehensive insights into SPO, which verifies its effectiveness. The code is available at https://github.com/lijian16/SPO., Comment: Accepted at EMNLP 2024 Findings

Interference, a key concept in causal inference, extends the reward modeling process by accounting for the impact of one unit's actions on the rewards of others. In contextual bandit (CB) settings, where multiple units are present in the same round, potential interference can significantly affect the estimation of expected rewards for different arms, thereby influencing the decision-making process. Although some prior work has explored multi-agent and adversarial bandits in interference-aware settings, the effect of interference in CB, as well as the underlying theory, remains significantly underexplored. In this paper, we introduce a systematic framework to address interference in Linear CB (LinCB), bridging the gap between causal inference and online decision-making. We propose a series of algorithms that explicitly quantify the interference effect in the reward modeling process and provide comprehensive theoretical guarantees, including sublinear regret bounds, finite sample upper bounds, and asymptotic properties. The effectiveness of our approach is demonstrated through simulations and a synthetic data generated based on MovieLens data.

Today's top advertisers typically manage hundreds of campaigns simultaneously and consistently launch new ones throughout the year. A crucial challenge for marketing managers is determining the optimal allocation of limited budgets across various ad lines in each campaign to maximize cumulative returns, especially given the huge uncertainty in return outcomes. In this paper, we propose to formulate budget allocation as a multi-task combinatorial bandit problem and introduce a novel online budget allocation system. The proposed system: i) integrates a Bayesian hierarchical model to intelligently utilize the metadata of campaigns and ad lines and budget size, ensuring efficient information sharing; ii) provides the flexibility to incorporate diverse modeling techniques such as Linear Regression, Gaussian Processes, and Neural Networks, catering to diverse environmental complexities; and iii) employs the Thompson sampling (TS) technique to strike a balance between exploration and exploitation. Through offline evaluation and online experiments, our system demonstrates robustness and adaptability, effectively maximizing the overall cumulative returns. A Python implementation of the proposed procedure is available at https://anonymous.4open.science/r/MCMAB.

This paper presents our method for the generative track of The First Dataset Distillation Challenge at ECCV 2024. Since the diffusion model has become the mainstay of generative models because of its high-quality generative effects, we focus on distillation methods based on the diffusion model. Considering that the track can only generate a fixed number of images in 10 minutes using a generative model for CIFAR-100 and Tiny-ImageNet datasets, we need to use a generative model that can generate images at high speed. In this study, we proposed a novel generative dataset distillation method based on Stable Diffusion. Specifically, we use the SDXL-Turbo model which can generate images at high speed and quality. Compared to other diffusion models that can only generate images per class (IPC) = 1, our method can achieve an IPC = 10 for Tiny-ImageNet and an IPC = 20 for CIFAR-100, respectively. Additionally, to generate high-quality distilled datasets for CIFAR-100 and Tiny-ImageNet, we use the class information as text prompts and post data augmentation for the SDXL-Turbo model. Experimental results show the effectiveness of the proposed method, and we achieved third place in the generative track of the ECCV 2024 DD Challenge. Codes are available at https://github.com/Guang000/BANKO., Comment: The Third Place Winner in Generative Track of the ECCV 2024 DD Challenge

Topological superconductivity (TSC) is a promising platform to host Majorana zero mode (MZM) for topological quantum computing. Recently, the noble metal alloy AuSn$_{4}$ has been identified as an intrinsic surface TSC. However, the atomic visualization of its nontrivial surface states and MZM remains elusive. Here, we report the direct observation of unconventional surface states and vortex zero mode at the gold (Au) terminated surfaces of AuSn$_{4}$, by ultra-low scanning tunneling microscope/spectroscopy. Distinct from the trivial metallic bulk states at tin (Sn) surfaces, the Au terminated surface exhibits pronounced surface states near Fermi level. Our density functional theory calculations indicate that these states arise from unconventional Rashba bands, where two Fermi circles from different bands share identical helical spin textures, chiralities, and group velocities in the same direction. Furthermore, we find that although the superconducting gap, critical temperature, anisotropic in-plane critical field are almost identical on Au and Sn terminated surfaces, the in-gap bound states inside Abrikosov vortex cores show significant differences. The vortex on Sn terminated surfaces exhibits a conventional Caroli-de Gennes-Matricon bound state while the Au surface shows a sharp zero-energy core state with a long non-splitting distance, resembling an MZM in a non-quantum-limit condition. This distinction may result from the dominant contribution of unconventional Rashba bands near Fermi energy from Au terminated surface. Our results provide a new platform for studying unconventional Rashba band and MZM in superconductors., Comment: 17 pages, 4 figures

It is challenging for the mobile robot to achieve autonomous and mapless navigation in the unknown environment with uneven terrain. In this study, we present a layered and systematic pipeline. At the local level, we maintain a tree structure that is dynamically extended with the navigation. This structure unifies the planning with the terrain identification. Besides, it contributes to explicitly identifying the hazardous areas on uneven terrain. In particular, certain nodes of the tree are consistently kept to form a sparse graph at the global level, which records the history of the exploration. A series of subgoals that can be obtained in the tree and the graph are utilized for leading the navigation. To determine a subgoal, we develop an evaluation method whose input elements can be efficiently obtained on the layered structure. We conduct both simulation and real-world experiments to evaluate the developed method and its key modules. The experimental results demonstrate the effectiveness and efficiency of our method. The robot can travel through the unknown uneven region safely and reach the target rapidly without a preconstructed map., Comment: This paper has been accepted by 2024 IEEE International Conference on Robotics and Automation (ICRA 2024)

The scalability limitations of public blockchains have hindered their widespread adoption in real-world applications. While the Ethereum community is pushing forward in zk-rollup (zero-knowledge rollup) solutions, such as introducing the ``blob transaction'' in EIP-4844, Layer 2 networks encounter a data availability problem: storing transactions completely off-chain poses a risk of data loss, particularly when Layer 2 nodes are untrusted. Additionally, building Layer 2 blocks requires significant computational power, compromising the decentralization aspect of Layer 2 networks. This paper introduces new techniques to address the data availability and decentralization challenges in Layer 2 networks. To ensure data availability, we introduce the concept of ``proof of download'', which ensures that Layer 2 nodes cannot aggregate transactions without downloading historical data. Additionally, we design a ``proof of storage'' scheme that punishes nodes who maliciously delete historical data. For decentralization, we introduce a new role separation for Layer 2, allowing nodes with limited hardware to participate. To further avoid collusion among Layer 2 nodes, we design a ``proof of luck'' scheme, which also provides robust protection against maximal extractable value (MEV) attacks. Experimental results show our techniques not only ensure data availability but also improve overall network efficiency, which implies the practicality and potential of our techniques for real-world implementation.

In two-dimensional system with Rashba spin-orbit coupling, it is well-known that superconductivity can have mixed spin-singlet and -triplet parity, and the $\boldsymbol{d}$-vector of spin-triplet pairing is parallel to $\boldsymbol{g}$-vector of Rashba spin-orbit coupling. Here, we propose a model to describe a two-dimensional system with unconventional Rashba bands and study its superconductivity. We show that the $\boldsymbol{d}$-vector of spin-triplet pairing can be either parallel or perpendicular to $\boldsymbol{g}$-vector of Rashba spin-orbit coupling depending on the different pairing interaction. We also propose a junction to generate tunneling current depending on the direction of $\boldsymbol{d}$-vector. It provides a detectable evidence to distinguish these two different but very similar pairing channels. Furthermore, we find this model can give arise to a subleading spin-singlet chiral $p$-wave topological superconducting state. More significantly, we find that such unconventional Rashba bands and unconventional superconudcting pairings can be realized on surface of some superconducting topological materials, such as trigonal layered PtBi$_{2}$., Comment: 14 pages, 3 figures

In two-dimensional system, Rashba spin-orbit coupling can lift spin degeneracy and gives the opposite spin chirality of two split Fermi circles from two Rashba bands. Here, we propose a generic model which can produce unconventional Rashba bands. In such a case, the two Fermi circles from two bands have the same spin chirality. When various interactions are taken into account, many unique physics can emerge in case of unconventional Rashba bands in comparison with in case of conventional Rashba bands. For instance, we study the spin galvanic effect by considering two cases with potential impurity scattering and magnetic impurity scattering, respectively. In both cases, we find the efficiency of spin galvanic effect is strongly enhanced in unconventional Rashba bands in comparison with conventional Rashba bands. More intriguingly, we find the effeiciency of conventional Rashba bands is insensitive to potential or magnetic impurity scattering. However, such efficiency of uncoventional Rashba bands can be further enhanced by the magnetic impurity scattering in comparison with the potential impurity scattering. Thus, the unconventional Rashba bands can give giant spin galvanic effect. These results show that this model is useful to explore abnormal physics in the systems with unconventional Rashba bands., Comment: 14 pages, 8 figures

Cooperative perception offers several benefits for enhancing the capabilities of autonomous vehicles and improving road safety. Using roadside sensors in addition to onboard sensors increases reliability and extends the sensor range. External sensors offer higher situational awareness for automated vehicles and prevent occlusions. We propose CoopDet3D, a cooperative multi-modal fusion model, and TUMTraf-V2X, a perception dataset, for the cooperative 3D object detection and tracking task. Our dataset contains 2,000 labeled point clouds and 5,000 labeled images from five roadside and four onboard sensors. It includes 30k 3D boxes with track IDs and precise GPS and IMU data. We labeled eight categories and covered occlusion scenarios with challenging driving maneuvers, like traffic violations, near-miss events, overtaking, and U-turns. Through multiple experiments, we show that our CoopDet3D camera-LiDAR fusion model achieves an increase of +14.36 3D mAP compared to a vehicle camera-LiDAR fusion model. Finally, we make our dataset, model, labeling tool, and dev-kit publicly available on our website: https://tum-traffic-dataset.github.io/tumtraf-v2x.

Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bounding boxes or bird's eye views as representations of the environment. However, these approaches fall short in offering a comprehensive 3D environmental prediction. To bridge this gap, we introduce the first method for collaborative 3D semantic occupancy prediction. Particularly, it improves local 3D semantic occupancy predictions by hybrid fusion of (i) semantic and occupancy task features, and (ii) compressed orthogonal attention features shared between vehicles. Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation. The experimental findings highlight that: (i) our collaborative semantic occupancy predictions excel above the results from single vehicles by over 30%, and (ii) models anchored on semantic occupancy outpace state-of-the-art collaborative 3D detection techniques in subsequent perception applications, showcasing enhanced accuracy and enriched semantic-awareness in road environments., Comment: Accepted by CVPR2024. Website link: https://rruisong.github.io/publications/CoHFF

This paper provides robust estimators and efficient inference of causal effects involving multiple interacting mediators. Most existing works either impose a linear model assumption among the mediators or are restricted to handle conditionally independent mediators given the exposure. To overcome these limitations, we define causal and individual mediation effects in a general setting, and employ a semiparametric framework to develop quadruply robust estimators for these causal effects. We further establish the asymptotic normality of the proposed estimators and prove their local semiparametric efficiencies. The proposed method is empirically validated via simulated and real datasets concerning psychiatric disorders in trauma survivors.

This paper explores the causal reasoning of large language models (LLMs) to enhance their interpretability and reliability in advancing artificial intelligence. Despite the proficiency of LLMs in a range of tasks, their potential for understanding causality requires further exploration. We propose a novel causal attribution model that utilizes ``do-operators" for constructing counterfactual scenarios, allowing us to systematically quantify the influence of input numerical data and LLMs' pre-existing knowledge on their causal reasoning processes. Our newly developed experimental setup assesses LLMs' reliance on contextual information and inherent knowledge across various domains. Our evaluation reveals that LLMs' causal reasoning ability mainly depends on the context and domain-specific knowledge provided. In the absence of such knowledge, LLMs can still maintain a degree of causal reasoning using the available numerical data, albeit with limitations in the calculations. This motivates the proposed fine-tuned LLM for pairwise causal discovery, effectively leveraging both knowledge and numerical information., Comment: A Python implementation of our proposed method is available at https://github.com/ncsulsj/Causal_LLM

Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts, such as causal decision-making is still limited. In this work, we explore the possibility of fine-tuning an open-sourced LLM into LLM4Causal, which can identify the causal task, execute a corresponding function, and interpret its numerical results based on users' queries and the provided dataset. Meanwhile, we propose a data generation process for more controllable GPT prompting and present two instruction-tuning datasets: (1) Causal-Retrieval-Bench for causal problem identification and input parameter extraction for causal function calling and (2) Causal-Interpret-Bench for in-context causal interpretation. By conducting end-to-end evaluations and two ablation studies, we showed that LLM4Causal can deliver end-to-end solutions for causal problems and provide easy-to-understand answers, which significantly outperforms the baselines., Comment: Accepted by COLM2024

Cross-domain text classification aims to transfer models from label-rich source domains to label-poor target domains, giving it a wide range of practical applications. Many approaches promote cross-domain generalization by capturing domain-invariant features. However, these methods rely on unlabeled samples provided by the target domains, which renders the model ineffective when the target domain is agnostic. Furthermore, the models are easily disturbed by shortcut learning in the source domain, which also hinders the improvement of domain generalization ability. To solve the aforementioned issues, this paper proposes TACIT, a target domain agnostic feature disentanglement framework which adaptively decouples robust and unrobust features by Variational Auto-Encoders. Additionally, to encourage the separation of unrobust features from robust features, we design a feature distillation task that compels unrobust features to approximate the output of the teacher. The teacher model is trained with a few easy samples that are easy to carry potential unknown shortcuts. Experimental results verify that our framework achieves comparable results to state-of-the-art baselines while utilizing only source domain data., Comment: Accepted by AAAI-2024

Many real applications of bandits have sparse non-zero rewards, leading to slow learning speed. Using problem-specific structures for careful distribution modeling is known as critical to estimation efficiency in statistics, yet is under-explored in bandits. We initiate the study of zero-inflated bandits, where the reward is modeled as a classic semi-parametric distribution called zero-inflated distribution. We design Upper Confidence Bound- and Thompson Sampling-type algorithms for this specific structure. We derive the regret bounds under both multi-armed bandits with general reward assumptions and contextual generalized linear bandit with sub-Gaussian rewards. In many settings, the regret rates of our algorithms are either minimax optimal or state-of-the-art. The superior empirical performance of our methods is demonstrated via numerical studies.

The selection of the assumed effect size (AES) critically determines the duration of an experiment, and hence its accuracy and efficiency. Traditionally, experimenters determine AES based on domain knowledge. However, this method becomes impractical for online experimentation services managing numerous experiments, and a more automated approach is hence of great demand. We initiate the study of data-driven AES selection in for online experimentation services by introducing two solutions. The first employs a three-layer Gaussian Mixture Model considering the heteroskedasticity across experiments, and it seeks to estimate the true expected effect size among positive experiments. The second method, grounded in utility theory, aims to determine the optimal effect size by striking a balance between the experiment's cost and the precision of decision-making. Through comparisons with baseline methods using both simulated and real data, we showcase the superior performance of the proposed approaches.

With the rise of two-dimensional (2D) materials, unique properties that are completely distinct from bulk counterparts continue to emerge at low-dimensional scales, presenting numerous opportunities and challenges. It also provides a new perspective for the study of transition metal system. Here, based on density functional theory (DFT), the physical properties of 2D monolayer LiV2S4 have been studied. Remarkable changes have been observed, i.e., vanadium dimerization, ferromagnetism, charge distribution and metal-insulator transition (MIT). It is argued that the electronic instability leads to the V dimerization which further lifts the degeneracy of charge distribution and stabilizes the charge and spin ordering state., Comment: 6 pages, 5 Figures

Let $G=(V,E)$ be a simple connected graph with vertex set $V(G)$ and edge set $E(G)$. The third atom-bond connectivity index, $ABC_3$ index, of $G$ is defined as $ABC_3(G)=\sum\limits_{uv\in E(G)}\sqrt{\frac{e(u)+e(v)-2}{e(u)e(v)}}$, where eccentricity $e(u)$ is the largest distance between $u$ and any other vertex of $G$, namely $e(u)=\max\{d(u,v)|v\in V(G)\}$. This work determines the maximal $ABC_3$ index of unicyclic graphs with any given girth and trees with any given diameter, and characterizes the corresponding graphs.

Graovac-Ghorbani index is a new version of the atom-bond connectivity index. D. Pacheco et al. [D. Pacheco, L. de Lima, C. S. Oliveira, On the Graovac-Ghorbani Index for Bicyclic Graph with No Pendent Vertices, MATCH Commun. Math. Comput. Chem. 86 (2021) 429-448] conjectured a sharp lower and upper bounds to the Graovac-Ghorbani index for all bicyclic graphs. Motivated by their nice work, in this paper we determine the maximal Graovac-Ghorbani index of bicyclic graphs and characterize the corresponding extremal graphs, which solves one of their Conjectures.

Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world. However, LLMs can capture social biases from unprocessed training data and propagate the biases to downstream tasks. Unfair LLM systems have undesirable social impacts and potential harms. In this paper, we provide a comprehensive review of related research on fairness in LLMs. Considering the influence of parameter magnitude and training paradigm on research strategy, we divide existing fairness research into oriented to medium-sized LLMs under pre-training and fine-tuning paradigms and oriented to large-sized LLMs under prompting paradigms. First, for medium-sized LLMs, we introduce evaluation metrics and debiasing methods from the perspectives of intrinsic bias and extrinsic bias, respectively. Then, for large-sized LLMs, we introduce recent fairness research, including fairness evaluation, reasons for bias, and debiasing methods. Finally, we discuss and provide insight on the challenges and future directions for the development of fairness in LLMs., Comment: 28 pages, 5 figures, 2 tables, 175 references

Most self-supervised 6D object pose estimation methods can only work with additional depth information or rely on the accurate annotation of 2D segmentation masks, limiting their application range. In this paper, we propose a 6D object pose estimation method that can be trained with pure RGB images without any auxiliary information. We first obtain a rough pose initialization from networks trained on synthetic images rendered from the target's 3D mesh. Then, we introduce a refinement strategy leveraging the geometry constraint in synthetic-to-real image pairs from multiple different views. We formulate this geometry constraint as pixel-level flow consistency between the training images with dynamically generated pseudo labels. We evaluate our method on three challenging datasets and demonstrate that it outperforms state-of-the-art self-supervised methods significantly, with neither 2D annotations nor additional depth images., Comment: Accepted by ICCV 2023

Decentralized identity mechanisms endeavor to endow users with complete sovereignty over their digital assets within the Web3 ecosystem. Unfortunately, this benefit frequently comes at the expense of users' credential and identity privacy. Additionally, existing schemes fail to resist Sybil attacks that have long plagued Web3, and lack reasonable key recovery mechanisms to regain control of digital assets after loss. In this work, we propose LinkDID, a privacy-preserving, Sybil-resistant, and key-recoverable decentralized identity scheme that supports selective disclosure of credentials for arbitrary predicates while maintaining privacy for credentials and identities. Through an identifier association mechanism, LinkDID can privately and forcibly aggregate users' identifiers, providing Sybil resistance without relying on any external data or collateral from benign users. To enable key recovery, LinkDID permits users to establish proofs of ownership for identifiers with lost keys and request an update of corresponding keys from the decentralized ledger. We provide a detailed theoretical analysis and security proofs of LinkDID, along with an exhaustive performance evaluation that shows its ability to complete interactions in less than 10 seconds on consumer-grade devices., Comment: 20 pages

Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a superficial association with the label, resulting in a false prediction. Conversely, shortcut learning can be mitigated if the model relies on robust causal features that help produce sound predictions. To this end, many studies have explored post-hoc interpretable methods to mine shortcuts and causal features for robustness and generalization. However, most existing methods focus only on single word in a sentence and lack consideration of word-group, leading to wrong causal features. To solve this problem, we propose a new Word-Group mining approach, which captures the causal effect of any keyword combination and orders the combinations that most affect the prediction. Our approach bases on effective post-hoc analysis and beam search, which ensures the mining effect and reduces the complexity. Then, we build a counterfactual augmentation method based on the multiple word-groups, and use an adaptive voting mechanism to learn the influence of different augmentated samples on the prediction results, so as to force the model to pay attention to effective causal features. We demonstrate the effectiveness of the proposed method by several tasks on 8 affective review datasets and 4 toxic language datasets, including cross-domain text classificaion, text attack and gender fairness test., Comment: 13 pages, 7 figures

Most recent 6D object pose methods use 2D optical flow to refine their results. However, the general optical flow methods typically do not consider the target's 3D shape information during matching, making them less effective in 6D object pose estimation. In this work, we propose a shape-constraint recurrent matching framework for 6D object pose estimation. We first compute a pose-induced flow based on the displacement of 2D reprojection between the initial pose and the currently estimated pose, which embeds the target's 3D shape implicitly. Then we use this pose-induced flow to construct the correlation map for the following matching iterations, which reduces the matching space significantly and is much easier to learn. Furthermore, we use networks to learn the object pose based on the current estimated flow, which facilitates the computation of the pose-induced flow for the next iteration and yields an end-to-end system for object pose. Finally, we optimize the optical flow and object pose simultaneously in a recurrent manner. We evaluate our method on three challenging 6D object pose datasets and show that it outperforms the state of the art significantly in both accuracy and efficiency., Comment: CVPR 2023

Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services. Federated learning (FL) overcomes privacy constraints by training ML models in distributed systems, exchanging model parameters instead of raw data. However, the dynamic states of connected vehicles affect the network connection quality and influence the FL performance. To tackle this challenge, we propose a contextual client selection pipeline that uses Vehicle-to-Everything (V2X) messages to select clients based on the predicted communication latency. The pipeline includes: (i) fusing V2X messages, (ii) predicting future traffic topology, (iii) pre-clustering clients based on local data distribution similarity, and (iv) selecting clients with minimal latency for future model aggregation. Experiments show that our pipeline outperforms baselines on various datasets, particularly in non-iid settings., Comment: Accepted at ICRA 2023 Workshop on Collaborative Perception and Learning