ICLR 2026 论文列表

We propose a general framework for causal Imitation Learning (IL) with hidden confounders, which subsumes several existing settings. Our framework accounts for two types of hidden confounders: (a) variables observed by the expert but not by the imitator, and (b) confounding noise hidden from both. By leveraging trajectory histories as instruments, we reformulate causal IL in our framework into a Conditional Moment Restriction (CMR) problem. We propose DML-IL, an algorithm that solves this CMR problem via instrumental variable regression, and upper bound its imitation gap. Empirical evaluation on continuous state-action environments, including Mujoco tasks, demonstrates that DML-IL outperforms existing causal IL baselines.

When a predictive model anticipates an undesired future event, a question arises: what can we do to avoid it? Resolving this forward-looking challenge requires determining the variables that positively influence the future, moving beyond statistical correlations typically exploited for prediction. In this paper, we introduce a novel framework for evaluating the influence of actionable variables in successfully avoiding the undesired future. We quantify influence as the degree to which the probability of success can be increased by altering variables based on the principle of maximum expected utility. While closely related to causal effects, our analysis reveals a counterintuitive insight: influential variables may not necessarily be those with intrinsically strong causal effects on the target. In fact, due to the dynamics of the decision process, it can be highly beneficial to alter a weak causal factor, or even a variable that is not an intrinsic factor at all. We provide a practical implementation for computing the proposed quantity using observational data and demonstrate its utility through empirical studies on synthetic and real-world applications.

Identifying latent variables and their induced causal structure is fundamental in various scientific fields. Existing approaches often rely on restrictive structural assumptions (e.g., purity) and may become invalid when these assumptions are violated. We introduce Conditional Independent Component Analysis (CICA), a new tool that extracts components that are conditionally independent given latent variables. Under mild conditions, CICA can be optimized using a tractable proxy such as rank-deficiency constraints. Building on CICA, we establish an identifiability theory for linear non-Gaussian acyclic models with latent variables: solving CICA and then applying an appropriate row permutation to the sparsest CICA solution enables recovery of the causal structure. Accordingly, we propose an estimation method based on the identifiability theory and substantiate the algorithm with experiments on both synthetic and real-world datasets.

Federated Recommender Systems (FRS) preserve privacy by training decentralized models on client-specific user-item subgraphs without sharing raw data. However, FRS faces a unique challenge: subgraph structural imbalance, where drastic variations in subgraph scale (user/item counts) and connectivity (item degree) misalign client representations, making it challenging to train a robust model that respects each client’s unique structural characteristics. To address this, we propose a Low-pass Personalized Subgraph Federated recommender system (LPSFed). LPSFed leverages graph Fourier transforms and low-pass spectral filtering to extract low-frequency structural signals that remain stable across subgraphs of varying size and degree, allowing robust personalized parameter updates guided by similarity to a neutral structural anchor. Additionally, we leverage a localized popularity bias-aware margin that captures item-degree imbalance within each subgraph and incorporates it into a personalized bias correction term to mitigate recommendation bias. Supported by theoretical analysis and validated on five real-world datasets, LPSFed achieves superior recommendation accuracy and enhances model robustness.

Existing Temporal Knowledge Graph (TKG) representation learning approaches focus on modeling entity correlations. However, since TKG datasets are constructed from events, which inherently contain heterogeneous causalities, focusing solely on entity or relation level correlations is inadequate for event prediction in TKGs. Although a TKG structural causal model can be established as a theoretical framework for event level causality disentangling, practical disentanglement is non-trivial due to the lack of explicit supervision signals. To this end, we propose a Heterogeneous Event causality Disentangling Representation learning Approach (HEDRA) for TKG reasoning, which is the first work that focuses on disentangling heterogeneous causalities at the event level in TKGs. Specifically, a counterfactual detector module is proposed to disentangle non-causality by leveraging event importance and distributional discrepancies of event representations. Moreover, an Instrumental Variable (IV)-guided disentangling module is proposed to disentangle spurious causality by constructing IVs, which can produce robust event representations against spurious causality through multi-view causality subgraphs. Finally, an evolutionary orthogonal module is proposed to separate dynamic causality from static causality for event prediction. Comprehensive experiments on five real-world datasets demonstrate that HEDRA achieves the state-of-the-art performance. The source code of HEDRA is available at https://anonymous.4open.science/r/HEDRA-8A2F.

We introduce a unified framework for contextual and causal Bayesian optimisation, which aims to design intervention policies maximising the expectation of a target variable. Our approach leverages both observed contextual information and known causal graph structures to guide the search. Within this framework, we propose a novel algorithm that jointly optimises over policies and the sets of variables on which these policies are defined. This thereby extends and unifies two previously distinct approaches: Causal Bayesian Optimisation and Contextual Bayesian Optimisation, while also addressing their limitations in scenarios that yield suboptimal results. We derive worst-case and instance-dependent high-probability regret bounds for our algorithm. We report experimental results across diverse environments, corroborating that our approach achieves sublinear regret and reduces sample complexity in high-dimensional settings.

Large language models (LLMs) can solve complex real-world tasks when prompted to generate chain-of-thought (CoT) reasoning, motivating their use for preference reasoning in recommender systems. However, applying LLM reasoning on recommendation faces two practical challenges. First, LLMs struggle to reason over long, noisy user histories that often span hundreds of items while truncation discards signals needed to capture long-term interests. Second, in decoder-only architectures, CoT requires generating rationale tokens autoregressively, leading to prohibitive inference latency for real-world deployment. To address the challenges, we propose SIREN, a framework that enables effective LLM-based rating prediction via long-term interest sketching and internalized reasoning. First, instead of prompting raw histories, we build a compact, token-bounded interest sketch that preserves persistent preferences and suppresses noise. Specifically, we encode and cluster item descriptions to discover semantic topics, then compress each user’s history into a short list of liked and disliked topics, facilitating LLM reasoning. Second, we develop an internalized reasoning strategy for efficient inference. We adopt a two-stage training paradigm: (i) train the LLM to reason explicitly for rating prediction with rule-based reinforcement learning, since ground-truth CoTs are unavailable in recommendation; and (ii) learn to internalize CoT into model parameters through hidden alignment. At inference, the LLM directly generates the rating with near-CoT quality. Extensive experiments show that SIREN reduces average input tokens by $48.7\%$ compared to raw-history prompting, outperforms existing methods while delivering over $100\times$ lower inference latency than CoT-based LLM recommenders. Code and data are available at https://anonymous.4open.science/r/LLM4Rec-C7CF.

Sequential recommendation models are widely used in applications, yet they face stringent latency requirements. Mainstream models leverage the Transformer attention mechanism to improve performance, but its computational complexity grows with the sequence length, leading to a latency challenge for long sequences. Consequently, KV cache technology has recently been explored in sequential recommendation systems to reduce inference latency. However, KV cache introduces substantial storage overhead in sequential recommendation systems, which often have a large user base with potentially very long user history sequences. In this work, we observe that KV sequences across different users exhibit significant similarities, indicating the existence of collaborative signals in KV. Furthermore, we analyze the KV using singular value decomposition (SVD) and find that the information in KV can be divided into two parts: the majority of the information is shareable across users, while a small portion is user-specific. Motivated by this, we propose CollectiveKV, a cross-user KV sharing mechanism. It captures the information shared across users through a learnable global KV pool. During inference, each user retrieves high-dimensional shared KV from the pool and concatenates them with low-dimensional user-specific KV to obtain the final KV. Experiments on five sequential recommendation models and three datasets show that our method can compress the KV cache to only 0.8\% of its original size, while maintaining or even enhancing model performance.

Randomized Controlled Trials are one of the pillars of science; nevertheless, they rely on hand-crafted hypotheses and expensive analysis. Such constraints prevent causal effect estimation at scale, potentially anchoring on popular yet incomplete hypotheses. We propose to discover the unknown effects of a treatment directly from data. For this, we turn unstructured data from a trial into meaningful representations via pretrained foundation models and interpret them via a Sparse Auto Encoder. However, discovering significant causal effects at the neural level is not trivial due to multiple-testing issues and effects entanglement. To address these challenges, we introduce _Neural Effect Search_, a novel recursive procedure solving both issues by progressive stratification. After assessing the robustness of our algorithm on semi-synthetic experiments, we showcase, in the context of experimental ecology, the first successful unsupervised causal effect identification on a real-world scientific trial.

Complex causal systems with interdependent variables require inference from heterogeneous observations that vary in spatial resolution, temporal frequency, and noise characteristics due to data acquisition constraints. Existing multi-modal fusion approaches assume uniform data quality or complete observability -- assumptions often violated in real-world applications. Current methods face three limitations: they treat causally-related variables independently, failing to exploit causal relationships; they cannot integrate multi-resolution observations effectively; and they lack theoretical frameworks for cascaded approximation errors. We introduce the Score-based Variational Graphical Diffusion Model (SVGDM), which integrates score-based diffusion within causal graphical structures for inference under heterogeneous incomplete observations. SVGDM introduces causal score decomposition enabling information propagation across causally-connected variables while preserving original observation characteristics. Diffusion provides a natural way to model scale-dependent sensing noise, which is common in remote-sensing, climate, and physical measurement systems, while the causal graph encodes well-established mechanistic dependencies between latent processes. We provide theoretical analysis and demonstrate superior performance on both synthetic and real-world datasets compared to relevant baselines.

Cross-modal representation learning is fundamental for extracting structured information from multimodal data to enable semantic understanding and reasoning. However, current methods optimize statistical objectives without explicit causal constraints, where nonlinear mappings can introduce spurious dependencies or eliminate critical mediators, leading to representation-induced structural drift that undermines the reliability of causal inference. Therefore, establishing theoretical guarantees for causal invariance in cross-modal representation learning remains a foundational challenge. To this end, we propose Causal Alignment and Representation Learning (CARL), which explicitly embeds causal structure preservation constraints into cross-modal alignment objectives. Specifically, CARL introduces a multi-consistency loss architecture that jointly optimizes conditional independence preservation and information bottleneck regularization to balance cross-modal compression with critical variable retention, ensuring low-density modalities are not masked by high-density reconstruction demands. We further incorporate monotonic alignment consistency loss to establish correspondence between semantic similarity and representation distance through Spearman correlation, and Markov boundary preservation loss to maintain identifiability conditions including backdoor, frontdoor, and instrumental variable criteria in the shared representation space. In synthetic experiments with known causal ground truth, CARL achieves state-of-the-art performance in preserving conditional independence patterns and maintaining causal query identifiability under structural uncertainty. Real-world validation on Human Phenotype Project data reveals that CARL successfully preserves causal structures between fundus vascular representations and cardiovascular events, demonstrating its capacity for reliable cross-modal causal inference in complex biomedical applications.

Within heterogeneous treatment effect (HTE) analysis, various estimands have been proposed to capture the effect of a treatment conditional on covariates. Recently, the conditional quantile comparator (CQC) has emerged as a promising estimand, offering quantile-level summaries akin to the conditional quantile treatment effect (CQTE) while preserving some interpretability of the conditional average treatment effect (CATE). It achieves this by summarising the treated response conditional on both the covariates and the untreated response. Despite these desirable properties, the CQC's current estimation is limited by the need to first estimate the difference in conditional cumulative distribution functions and then invert it. This inversion obscures the CQC estimate, hampering our ability to both model and interpret it. To address this, we propose the first direct estimator of the CQC, allowing for explicit modelling and parameterisation. This explicit parameterisation enables better interpretation of our estimate while also providing a means to constrain and inform the model. We show, both theoretically and empirically, that our estimation error depends directly on the complexity of the CQC itself, improving upon the existing estimation procedure. Furthermore, it retains the desirable double robustness property with respect to nuisance parameter estimation. We further show our method to outperform existing procedures in estimation accuracy across multiple data scenarios while varying sample size and nuisance error. Finally, we apply it to real-world data from an employment scheme, uncovering a reduced range of potential earnings improvement as participant age increases.

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for post-training large language models (LLMs) on complex reasoning tasks. Yet, the conditions under which RLVR yields robust generalization remain poorly understood. This paper provides an empirical study of RLVR generalization in the setting of probabilistic inference over causal graphical models. This setting offers two natural axes along which to examine generalization: (i) the level of the probabilistic query—associational, interventional, or counterfactual—and (ii) the structural complexity of the query, measured by the size of its relevant subgraph. We construct datasets of causal graphs and queries spanning these difficulty axes and fine-tune Qwen-2.5-Instruct models using RLVR or supervised fine-tuning (SFT). We vary both the model scale (3B–32B) and the query level included in training. We find that RLVR yields stronger within-level and across-level generalization than SFT, but only for specific combinations of model size and training query level. Further analysis shows that RLVR’s effectiveness depends on the model’s initial reasoning competence. With sufficient initial competence, RLVR improves an LLM’s marginalization strategy and reduces errors in intermediate probability calculations, producing substantial accuracy gains, particularly on more complex queries. These findings show that RLVR can improve specific causal reasoning subskills, with its benefits emerging only when the model has sufficient initial competence.

Why do reinforcement learning (RL) policies fail or succeed? This is a challenging question due to the complex, high-dimensional nature of agent-environment interactions. We take a causal perspective on explaining the global behavior of RL policies by viewing the states, actions, and rewards as variables in a low-level causal model. We introduce random perturbations to policy actions during execution and observe their effects on the cumulative reward, learning a simplified high-level causal model that explains these relationships. To this end, we develop a nonlinear Causal Model Reduction framework that ensures approximate interventional consistency, i.e., the simplified high-level model responds to interventions in a way consistent with the original complex system. \todo{make more convincing}We prove that for a class of nonlinear causal models, there exists a unique solution that achieves exact interventional consistency, ensuring learned explanations reflect meaningful causal patterns. Experiments on both synthetic causal models and practical RL tasks~-~including pendulum control and robot table tennis~-~demonstrate that our approach can uncover important behavioral patterns, biases, and failure modes in trained RL policies.

Estimating causal quantities (CQs) typically requires large datasets, which can be expensive to obtain, especially when measuring individual outcomes is costly. This challenge highlights the importance of sample-efficient active learning strategies. To address the narrow focus of prior work on the conditional average treatment effect, we formalize the broader task of Actively estimating Causal Quantities (ActiveCQ) and propose a unified framework for this general problem. Built upon the insight that many CQs are integrals of regression functions, our framework models the regression function with a Gaussian Process. For the distribution component, we explore both a baseline using explicit density estimators and a more integrated method using conditional mean embeddings in a reproducing kernel Hilbert space. This latter approach offers key advantages: it bypasses explicit density estimation, operates within the same function space as the GP, and adaptively refines the distributional model after each update. Our framework enables the principled derivation of acquisition strategies from the CQ's posterior uncertainty; we instantiate this principle with two utility functions based on information gain and total variance reduction. A range of simulated and semi-synthetic experiments demonstrate that our principled framework significantly outperforms relevant baselines, achieving substantial gains in sample efficiency across a variety of CQs.

Identifying the structure of a partially observed causal system is essential to various scientific fields. Recent advances have focused on constraint-based causal discovery to solve this problem, and yet in practice these methods often face challenges related to multiple testing and error propagation. These issues could be mitigated by a score-based method and thus it has raised great attention whether there exists a score-based greedy search method that can handle the partially observed scenario. In this work, we propose the first score-based greedy search method for the identification of structure involving latent variables with identifiability guarantees. Specifically, we propose Generalized N Factor Model and establish the global consistency: the true structure including latent variables can be identified up to the Markov equivalence class by using score. We then design Latent variable Greedy Equivalence Search (LGES), a greedy search algorithm for this class of model with well-defined operators, which search very efficiently over the graph space to find the optimal structure. Our experiments on both synthetic and real-life data validate the effectiveness of our method.

Understanding how neural networks transform inputs into outputs is crucial for interpreting and manipulating their behavior. Most existing approaches analyze internal representations by identifying hidden-layer activation patterns correlated with human-interpretable concepts. Here we take a direct approach to examine how hidden neurons act to drive network outputs. We introduce CODEC ($\textbf{Co}$ntribution $\textbf{Dec}$omposition), a method that uses sparse autoencoders to decompose network behavior into sparse motifs of hidden-neuron contributions, revealing causal processes that cannot be determined by analyzing activations alone. Applying CODEC to benchmark image-classification networks, we find that contributions grow in sparsity and dimensionality across layers and, unexpectedly, that they progressively decorrelate positive and negative effects on outputs. We further show that decomposing contributions into sparse modes enables greater control and interpretation of intermediate layers, supporting both causal manipulations of network output and human-interpretable visualizations of distinct image components that combine to drive that output. Finally, by analyzing state-of-the-art models of retinal activity, we demonstrate that CODEC uncovers combinatorial actions of model interneurons and identifies the sources of dynamic receptive fields. Overall, CODEC provides a rich and interpretable framework for understanding how nonlinear computations evolve across hierarchical layers, establishing contribution modes as an informative unit of analysis for mechanistic insights into artificial neural networks.

In many applications, treatment and outcome are confounded by unobservables, yet mediators remain unconfounded. The front‑door (FD) adjustment identifies causal effects through mediators even with unmeasured confounding. However, most estimators focus on *average treatment effects*, and work on *heterogeneous treatment effect* (HTE) estimation remain scarce. We address this gap with two *debiased* learners for heterogeneous FD effects: *FD‑DR‑Learner* and *FD‑R‑Learner*. Both attain fast, quasi-oracle rates (i.e., performance comparable to an oracle that knows the nuisances) even when nuisance functions converge as slowly as $n^{-1/4}$. Beyond theory, we demonstrate fast convergence and debiasedness in synthetic and real-world evaluations. Our results show that the proposed learners deliver robust and debiased HTE estimates under the FD scenario.

Existing causal discovery methods are fundamentally limited by the assumption of a static causal graph, a constraint that fails in real-world systems where causal relationships dynamically vary with underlying system parameters. This discrepancy prevents the application of causal discovery in critical domains such as industrial process control, where understanding how causal effects change is essential. We address this gap by proposing a new paradigm that moves beyond static graphs to learn functional causal representations. We introduce a framework that models each causal link not as a static weight but as a function of measurable system parameters. By representing these functions using Polynomial Chaos Expansions (PCE), we develop a tractable method to learn the complete parametric causal structure from observational data. We provide theoretical proofs for the identifiability of these functional models and introduce a novel, provably convergent learning algorithm. On a large-scale chemical reactor dataset, our method learns the dynamic causal structure with a 90.9% F1-score, nearly doubling the performance of state-of-the-art baselines and providing an interpretable model of how causal mechanisms evolve.