Recently, structure–text contrastive learning has shown promising performance on text-attributed graphs by leveraging the complementary strengths of graph neural networks and language models. However, existing methods typically rely on homophily assumptions in similarity estimation and hard optimization objectives, which limit their applicability to heterophilic graphs. Although existing methods can mitigate heterophily through structural adjustments or neighbor aggregation, they usually treat textual embeddings as static targets, leading to suboptimal alignment. In this work, we identify the multi-granular heterophily in text-attributed graphs, including complete heterophily, partial heterophily, and latent homophily, which makes structure–text alignment particularly challenging due to mixed, noisy, and missing semantic correlations. To achieve flexible and bidirectional alignment, we propose GCL-OT, a novel graph contrastive learning framework with optimal transport, equipped with tailored mechanisms for each type of heterophily. Specifically, for partial heterophily, we design a RealSoftMax-based similarity estimator to emphasize key neighbor-word interactions while easing background noise. For complete heterophily, we introduce a prompt-based filter that adaptively excludes irrelevant noise during optimal transport alignment. Furthermore, we incorporate OT-guided soft supervision to uncover potential neighbors with similar semantics, enhancing the learning of latent homophily. Theoretical analysis shows that GCL-OT can improve the mutual information bound and Bayes error guarantees. Extensive experiments on nine benchmarks show that GCL-OT outperforms state-of-the-art methods, demonstrating its effectiveness and robustness.

Zihao Li, Lecheng Zheng, Bowen Jin, Dongqi Fu, Baoyu Jing, Yikun Ban, Jingrui He, Jiawei Han. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its performance is highly dependent on the quality of the underlying human preference data. To address this bottleneck, prior work has explored various data selection strategies, but these methods often overlook the impact of the evolving states of the language model during the optimization process. In this paper, we introduce a novel problem: Sample Scheduling for DPO, which aims to dynamically and adaptively schedule training samples based on the model's evolving batch-wise states throughout preference optimization. To solve this problem, we propose SamS, an efficient and effective algorithm that adaptively selects samples in each training batch based on the LLM's learning feedback to maximize the potential generalization performance. Notably, without modifying the core DPO algorithm, simply integrating SamS significantly improves performance across tasks, with minimal additional computational overhead. This work points to a promising new direction for improving LLM alignment through batch-wise sample selection, with potential generalization to RLHF and broader supervised learning paradigms.

Large language models are typically adapted to downstream tasks through supervised fine-tuning on domain-specific data. While standard fine-tuning focuses on minimizing generation loss to optimize model parameters, we take a deeper step by retaining and leveraging the model’s own learning signals, analogous to how human learners reflect on past mistakes to improve future performance. We first introduce the concept of Mistake Log to systematically track the model’s learning behavior and recurring errors throughout fine-tuning. Treating the original transformer-based model as the Pilot, we correspondingly design a Copilot model to refine the Pilot’s inference performance via logits rectification. We name the overall Pilot-Copilot framework the Transformer Copilot, which introduces (i) a novel Copilot model design, (ii) a joint training paradigm where the Copilot continuously learns from the evolving Mistake Log alongside the Pilot, and (iii) a fused inference paradigm where the Copilot rectifies the Pilot’s logits for enhanced generation. We provide both theoretical and empirical analyses on our new learning framework. Experiments on 12 benchmarks spanning commonsense, arithmetic, and recommendation tasks demonstrate that Transformer Copilot consistently improves performance by up to 34.5%, while introducing marginal computational overhead to Pilot models and exhibiting strong scalability and transferability. Our code is released at https://github.com/jiaruzouu/TransformerCopilot.

Information diffusion prediction, aimed at estimating future interacting users for a given content, is crucial for various applications on online social platforms. Recently, methods based on dynamic graph learning have achieved superior performance. However, these methods often face scalability issues due to their full-neighbor aggregation, which requires loading the whole diffusion graph, making them impractical for large graphs. While improving model scalability through sampling is an immediate approach, it is challenging on the diffusion graph due to various user dependencies (i.e., the temporal and structural correlations of user–item interactions). To address this problem, we propose a new model named ASDIP, which performs adaptive sampling on the diffusion graph. Specifically, ASDIP employs multiple sampling strategies to extract walks from the diffusion graph, each identifying a representative user dependency by sampling walks that satisfy a specific temporal constraint. Next, the walks sampled by different strategies are first mapped into distinct strategy-specific user representations and then merged into a unified user representation, adaptively fusing the information obtained from different strategies. Finally, a cascade representation learning module is proposed to generate cascade representations based on user representations and interaction timestamps. Experimental results validate the effectiveness and scalability of ASDIP.

We study both stream-based and pool-based active learning with neural network approximations. A recent line of works proposed bandit-based approaches that transformed active learning into a bandit problem, achieving both theoretical and empirical success. However, the performance and computational costs of these methods may be susceptible to the number of classes, denoted as $K$, due to this transformation. Therefore, this paper seeks to answer the question: "How can we mitigate the adverse impacts of $K$ while retaining the advantages of principled exploration and provable performance guarantees in active learning?" To tackle this challenge, we propose two algorithms based on the newly designed exploitation and exploration neural networks for stream-based and pool-based active learning. Subsequently, we provide theoretical performance guarantees for both algorithms in a non-parametric setting, demonstrating a slower error-growth rate concerning $K$ for the proposed approaches. We use extensive experiments to evaluate the proposed algorithms, which consistently outperform state-of-the-art baselines.

Recent works have shown a reduction from contextual bandits to online regression under a realizability assumption (Foster and Rakhlin, 2020; Foster and Krishnamurthy, 2021). In this work, we investigate the use of neural networks for such online regression and associated Neural Contextual Bandits (NeuCBs). Using existing results for wide networks, one can readily show a ${\mathcal{O}}(\sqrt{T})$ regret for online regression with square loss, which via the reduction implies a ${\mathcal{O}}(\sqrt{K} T^{3/4})$ regret for NeuCBs. Departing from this standard approach, we first show a $\mathcal{O}(\log T)$ regret for online regression with almost convex losses that satisfy QG (Quadratic Growth) condition, a generalization of the PL (Polyak-\L ojasiewicz) condition, and that have a unique minima. Although not directly applicable to wide networks since they do not have unique minima, we show that adding a suitable small random perturbation to the network predictions surprisingly makes the loss satisfy QG with unique minima. Based on such a perturbed prediction, we show a ${\mathcal{O}}(\log T)$ regret for online regression with both squared loss and KL loss, and subsequently convert these respectively to $\tilde{\mathcal{O}}(\sqrt{KT})$ and $\tilde{\mathcal{O}}(\sqrt{KL^*} + K)$ regret for NeuCB, where $L^*$ is the loss of the best policy. Separately, we also show that existing regret bounds for NeuCBs are $\Omega(T)$ or assume i.i.d. contexts, unlike this work. Finally, our experimental results on various datasets demonstrate that our algorithms, especially the one based on KL loss, persistently outperform existing algorithms.

The contextual bandit has been identified as a powerful framework to formulate the recommendation process as a sequential decision-making process, where each item is regarded as an arm and the objective is to minimize the regret of T rounds. In this paper, we study a new problem, Clustering of Neural Bandits, by extending previous work to the arbitrary reward function, to strike a balance between user heterogeneity and user correlations in the recommender system. To solve this problem, we propose a novel algorithm called M-CNB, which utilizes a meta-learner to represent and rapidly adapt to dynamic clusters, along with an informative Upper Confidence Bound (UCB)-based exploration strategy. We provide an instance-dependent performance guarantee for the proposed algorithm that withstands the adversarial context, and we further prove the guarantee is at least as good as state-of-the-art (SOTA) approaches under the same assumptions. In extensive experiments conducted in both recommendation and online classification scenarios, M-CNB outperforms SOTA baselines. This shows the effectiveness of the proposed approach in improving online recommendation and online classification performance.

Link prediction is a critical problem in graph learning with broad applications such as recommender systems and knowledge graph completion. Numerous research efforts have been directed at solving this problem, including approaches based on similarity metrics and Graph Neural Networks (GNN). However, most existing solutions are still rooted in conventional supervised learning, which makes it challenging to adapt over time to changing customer interests and to address the inherent dilemma of exploitation versus exploration in link prediction. To tackle these challenges, this paper reformulates link prediction as a sequential decision-making process, where each link prediction interaction occurs sequentially. We propose a novel fusion algorithm, PRB (PageRank Bandits), which is the first to combine contextual bandits with PageRank for collaborative exploitation and exploration. We also introduce a new reward formulation and provide a theoretical performance guarantee for PRB. Finally, we extensively evaluate PRB in both online and offline settings, comparing it with bandit-based and graph-based methods. The empirical success of PRB demonstrates the value of the proposed fusion approach. Our code is released at https://github.com/jiaruzouu/PRB.

Contextual bandit algorithms aim to identify the optimal arm with the highest reward among a set of candidates, based on the accessible contextual information. Among these algorithms, neural contextual bandit methods have shown generally superior performances against linear and kernel ones, due to the representation power of neural networks. However, similar to other neural network applications, neural bandit algorithms can be vulnerable to adversarial attacks or corruptions on the received labels (i.e., arm rewards), which can lead to unexpected performance degradation without proper treatments. As a result, it is necessary to improve the robustness of neural bandit models against potential reward corruptions. In this work, we propose a novel neural contextual bandit algorithm named R-NeuralUCB, which utilizes a novel context-aware Gradient Descent (GD) training strategy to improve the robustness against adversarial reward corruptions. Under over-parameterized neural network settings, we provide regret analysis for R-NeuralUCB to quantify reward corruption impacts, without the commonly adopted arm separateness assumption in existing neural bandit works. We also conduct experiments against baselines on real data sets under different scenarios, in order to demonstrate the effectiveness of our proposed R-NeuralUCB.

Contextual bandits algorithms aim to choose the optimal arm with the highest reward out of a set of candidates based on the contextual information. Various bandit algorithms have been applied to real-world applications due to their ability of tackling the exploitation-exploration dilemma. Motivated by online recommendation scenarios, in this paper, we propose a framework named Graph Neural Bandits (GNB) to leverage the collaborative nature among users empowered by graph neural networks (GNNs). Instead of estimating rigid user clusters as in existing works, we model the "fine-grained" collaborative effects through estimated user graphs in terms of exploitation and exploration respectively. Then, to refine the recommendation strategy, we utilize separate GNN-based models on estimated user graphs for exploitation and adaptive exploration. Theoretical analysis and experimental results on multiple real data sets in comparison with state-of-the-art baselines are provided to demonstrate the effectiveness of our proposed framework.

Meta-learning has been proven an effective learning paradigm for training machine learning models with good generalization ability. Apart from the common practice of uniformly sampling the meta-training tasks, existing methods working on task scheduling strategies are mainly based on pre-defined sampling protocols or the assumed task-model correlations, and greedily make scheduling decisions, which can lead to sub-optimal performance bottlenecks of the meta-model. In this paper, we propose a novel task scheduling framework under Contextual Bandits settings, named BASS, which directly optimizes the task scheduling strategy based on the status of the meta-model. By balancing the exploitation and exploration in meta-learning task scheduling, BASS can help tackle the challenge of limited knowledge about the task distribution during the early stage of meta-training, while simultaneously exploring potential benefits for forthcoming meta-training iterations through an adaptive exploration strategy. Theoretical analysis and extensive experiments are presented to show the effectiveness of our proposed framework.

Disinformation refers to false information deliberately spread to influence the general public, and the negative impact of disinformation on society can be observed in numerous issues, such as political agendas and manipulating financial markets. In this paper, we identify prevalent challenges and advances related to automated disinformation detection from multiple aspects and propose a comprehensive and explainable disinformation detection framework called DISCO. It leverages the heterogeneity of disinformation and addresses the opaqueness of prediction. Then we provide a demonstration of DISCO on a real-world fake news detection task with satisfactory detection accuracy and explanation. The demo video and source code of DISCO is now publicly available https://github.com/DongqiFu/DISCO. We expect that our demo could pave the way for addressing the limitations of identification, comprehension, and explainability as a whole.

Contextual bandits aim to identify among a set of arms the optimal one with the highest reward based on their contextual information. Motivated by the fact that the arms usually exhibit group behaviors and the mutual impacts exist among groups, we introduce a new model, Arm Group Graph (AGG), where the nodes represent the groups of arms and the weighted edges formulate the correlations among groups. To leverage the rich information in AGG, we propose a bandit algorithm, AGG-UCB, where the neural networks are designed to estimate rewards, and we propose to utilize graph neural networks (GNN) to learn the representations of arm groups with correlations. To solve the exploitation-exploration dilemma in bandits, we derive a new upper confidence bound (UCB) built on neural networks (exploitation) for exploration. Furthermore, we prove that AGG-UCB can achieve a near-optimal regret bound with over-parameterized neural networks, and provide the convergence analysis of GNN with fully-connected layers which may be of independent interest. In the end, we conduct extensive experiments against state-of-the-art baselines on multiple public data sets, showing the effectiveness of the proposed algorithm.

We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. In particular, we introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work. Then, the proposed algorithm leverages the powerful representation of NNs for both exploitation and exploration, has the query decision-maker tailored for $k$-class classification problems with the performance guarantee, utilizes the full feedback, and updates parameters in a more practical and efficient manner. These careful designs lead to an instance-dependent regret upper bound, roughly improving by a multiplicative factor $O(\log T)$ and removing the curse of input dimensionality. Furthermore, we show that the algorithm can achieve the same performance as the Bayes-optimal classifier in the long run under the hard-margin setting in classification problems. In the end, we use extensive experiments to evaluate the proposed algorithm and SOTA baselines, to show the improved empirical performance.

Knowledge graph (KG for short) alignment aims at building a complete KG by linking the shared entities across complementary KGs. Existing approaches assume that KGs are static, despite the fact that almost every KG evolves over time. In this paper, we introduce the task of dynamic knowledge graph alignment, the main challenge of which is how to efficiently update entity embeddings for the evolving graph topology. Our key insight is to view the parameter matrix of GCN as a feature transformation operator and decouple the transformation process from the aggregation process. Based on that, we first propose a novel base algorithm (DINGAL-B) with topology-invariant mask gate and highway gate, which consistently outperforms 14 existing knowledge graph alignment methods in the static setting. More importantly, it naturally leads to two effective and efficient algorithms to align dynamic knowledge graph, including (1) DINGAL-O which leverages previous parameter matrices to update the embeddings of affected entities; and (2) DINGAL-U which resorts to newly obtained anchor links to fine-tune parameter matrices. Compared with their static counterpart (DINGAL-B), DINGAL-U and DINGAL-O are 10× and 100× faster respectively, with little alignment accuracy loss.

Contextual multi-armed bandit has shown to be an effective tool in recommender systems. In this paper, we study a novel problem of multi-facet bandits involving a group of bandits, each characterizing the users' needs from one unique aspect. In each round, for the given user, we need to select one arm from each bandit, such that the combination of all arms maximizes the final reward. This problem can find immediate applications in E-commerce, healthcare, etc. To address this problem, we propose a novel algorithm, named MuFasa, which utilizes an assembled neural network to jointly learn the underlying reward functions of multiple bandits. It estimates an Upper Confidence Bound (UCB) linked with the expected reward to balance between exploitation and exploration. Under mild assumptions, we provide the regret analysis of MuFasa. It can achieve the near-optimal Õ((K + 1) √T) regret bound where K is the number of bandits and T is the number of played rounds. Furthermore, we conduct extensive experiments to show that MuFasa outperforms strong baselines on real-world data sets.

We study identifying user clusters in contextual multi-armed bandits (MAB). Contextual MAB is an effective tool for many real applications, such as content recommendation and online advertisement. In practice, user dependency plays an essential role in the user’s actions, and thus the rewards. Clustering similar users can improve the quality of reward estimation, which in turn leads to more effective content recommendation and targeted advertising. Different from traditional clustering settings, we cluster users based on the unknown bandit parameters, which will be estimated incrementally. In particular, we define the problem of cluster detection in contextual MAB, and propose a bandit algorithm, LOCB, embedded with local clustering procedure. And, we provide theoretical analysis about LOCB in terms of the correctness and efficiency of clustering and its regret bound. Finally, we evaluate the proposed algorithm from various aspects, which outperforms state-of-the-art baselines.

In this paper, we study the problem of outlier arm detection in multi-armed bandit settings, which finds plenty of applications in many high-impact domains such as finance, healthcare, and online advertising. For this problem, a learner aims to identify the arms whose expected rewards deviate significantly from most of the other arms. Different from existing work, we target the generic outlier arms or outlier arm groups whose expected rewards can be larger, smaller, or even in between those of normal arms. To this end, we start by providing a comprehensive definition of such generic outlier arms and outlier arm groups. Then we propose a novel pulling algorithm named GOLD to identify such generic outlier arms. It builds a real-time neighborhood graph based on upper confidence bounds and catches the behavior pattern of outliers from normal arms. We also analyze its performance from various aspects. In the experiments conducted on both synthetic and real-world data sets, the proposed algorithm achieves 98% accuracy while saving 83% exploration cost on average compared with state-of-the-art techniques.

Many approaches focus on detecting dense blocks in the tensor of multimodal data to prevent fraudulent entities (e.g., accounts, links) from retweet boosting, hashtag hijacking, link advertising, etc. However, no existing method is effective to find the dense block if it only possesses high density on a subset of all dimensions in tensors. In this paper, we novelly identify dense-block detection with dense-subgraph mining, by modeling a tensor into a weighted graph without any density information lost. Based on the weighted graph, which we call information sharing graph (ISG), we propose an algorithm for finding multiple densest subgraphs, D-Spot, that is faster (up to 11x faster than the state-of-the-art algorithm) and can be computed in parallel. In an N-dimensional tensor, the entity group found by the ISG+D-Spot is at least 1/2 of the optimum with respect to density, compared with the 1/N guarantee ensured by competing methods. We use nine datasets to demonstrate that ISG+D-Spot becomes new state-of-the-art dense-block detection method in terms of accuracy specifically for fraud detection.