ICLR 2026 Papers

Persistent homology (PH) based schemes help encode information, such as cycles, and are thus increasingly being integrated with graph neural networks (GNNs) and higher order message-passing networks. Many PH based schemes in graph learning employ inclusion-based filtration mechanisms that trace a sequence of subgraphs of increasing size, maintaining bookkeeping information about the evolution (e.g., in terms of birth and death of components). We offer a novel perspective that goes beyond this inclusion paradigm. Specifically, we introduce topological descriptors for graphs, simplices, and cells that interleave a sequence of inclusions with a sequence of contractions and related families parametrized by two functions. The resulting descriptors on the extended sequence are provably more expressive than many existing PH methods with suitable stability conditions. Empirical results substantiate the merits of the proposed approach.

Knowledge Graph Question Answering (KGQA) aims to interpret natural language queries and perform structured reasoning over knowledge graphs by leveraging their relational and semantic structures to retrieve accurate answers. Existing methods primarily follow either the retrieve-then-reason paradigm, which relies on Graph Neural Networks (GNNs) or heuristic rules to extract static candidate paths, or dynamic path generation strategies that employ large language models (LLMs) with prompting to jointly perform retrieval and reasoning. However, the former lacks adaptability due to static path extraction and the absence of contextual refinement, while the latter suffers from high computational costs and limited evaluation accuracy because of their dependence on fixed scoring functions and repeated LLM calls. To address these issues, this paper proposes Dynamically Adaptive MCTS-based Reasoning (DAMR), a novel framework that integrates LLM-guided Monte Carlo Tree Search (MCTS) with adaptive path evaluation to enable efficient and context-aware KGQA. DAMR leverages MCTS as a backbone, where an LLM-based planner selects the top-$k$ semantically relevant relations at each expansion step to effectively reduce the search space. To enhance evaluation accuracy, we introduce a lightweight Transformer-based scorer that performs context-aware plausibility estimation by jointly encoding the question and relation sequence through cross-attention, thereby capturing fine-grained semantic shifts during multi-hop reasoning. Furthermore, to mitigate the scarcity of high-quality supervision, DAMR incorporates a dynamic pseudo-path refinement mechanism that periodically generates training signals from partial paths explored during search, enabling the scorer to continually adapt to the evolving distribution of reasoning trajectories. Extensive experiments on multiple KGQA benchmarks show that DAMR significantly outperforms state-of-the-art methods.

Graph Neural Networks (GNNs) have made significant advances in representation learning on various types of graph-structured data. However, GNNs struggle to simultaneously model heterophily and homophily, a challenge that is amplified under self-supervised learning (SSL) where no labels are available to guide the training process. This paper presents H$^3$GNNs, an end-to-end graph SSL framework designed to harmonize heterophily and homophily through two complementary innovative perspectives: (i) Representation Harmonization via Joint Structural Node Encoding. Nodes are embedded into a unified latent space that retains both node specificity and graph structural awareness for harmonizing heterophily and homophily. Node specificity is learned via linear and non-linear node feature projections. Graph structural awareness is learned via a proposed Weighted Graph Convolutional Network (WGCN). A self-attention module enables the model learning-to-adapt to varying levels of patterns. (ii) Objective Harmonization via Predictive Architecture with Node-Difficulty–Aware Masking. A teacher network processes the full graph. A student network receives a partially masked graph. The student is trained end-to-end, while the teacher is an exponential moving average of the student. The proxy task is to train the student to predict the teacher’s embeddings for all nodes (masked and unmasked). To keep the objective informative across the graph, two masking strategies that guide selection toward currently hard nodes while retaining exploration are proposed. Theoretical underpinnings of H$^3$GNNs are also analyzed in detail. Comprehensive evaluations on benchmarks demonstrate that H$^3$GNNs achieves state-of-the-art performance on heterophilic graphs (e.g., +7.1% on Texas, +9.6% on Roman-Empire over the prior art) while matching SOTA on homophilic graphs, and delivering strong computational efficiency.

Large language models (LLMs) have demonstrated remarkable generalization across diverse tasks, suggesting the existence of task-agnostic, generalizable knowledge encoded within them. However, how to systematically extract and evaluate this knowledge remains unexplored. In this work, we innovatively propose MASA (Matrix-level Alignment and Scalable Adaptation), a unified framework for extracting and transferring generalizable knowledge from LLMs. MASA first introduces a lightweight set of gene matrices trained with a dual alignment strategy, combining output alignment and spectral alignment, to capture the generalizable knowledge encoded in the feed-forward networks (FFNs) of LLM. It then employs scalable adaptation to flexibly reshape these gene matrices to match the parameter dimensions of lightweight dense models of various sizes, enabling direct initialization of their FFN layers. To evaluate the inherited knowledge, we measure the downstream performance of lightweight models initialized with MASA across language understanding and dialogue generation tasks spanning diverse vertical domains. Experiments on both dense and Mixture-of-Experts (MoE) source LLMs show that MASA consistently outperforms baselines such as random initialization, pruning, and distillation, yielding lightweight models that achieve stronger performance, require less pre-training data, and converge faster. These results establish MASA as an effective and general framework for extracting and leveraging the generalizable knowledge within LLMs.

Knowledge distillation is an efficient strategy to use data generated by large teacher language models to train smaller “capable” student models, but selecting the optimal teacher for a specific student-task combination requires expensive trial-and-error. We propose a lightweight score called GRACE to quantify how effective a teacher will be when post-training a student model to solve math problems. GRACE efficiently measures distributional properties of student gradients, and it can be computed without access to a verifier, teacher logits, teacher internals, or test data. From an information-theoretic perspective, GRACE measures leave-one-out stability in gradient-based algorithms, directly connecting it to the generalization performance of distilled student models. On GSM8K and MATH, GRACE correlates strongly (up to 86%) with the performance of the distilled Llama and OLMo students. In particular, training on GRACE-selected teacher provides at least a 6% improvement over naively using the best-performing teacher. We further demonstrate the utility of GRACE in providing guidance on crucial design choices in distillation, including (1) the best temperature to use when generating from the teacher, (2) the best teacher to use given a size constraint, and (3) the best teacher to use within a specific model family. Altogether, our findings demonstrate that GRACE can efficiently and effectively identify the most compatible teacher for a given student and provide fine-grained guidance on how to perform distillation.

Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a fast learner and a meta learner to address continual Reinforcement Learning~(RL) problems. These two learners are coupled to perform distinct yet complementary roles: the fast learner focuses on knowledge transfer, while the meta learner ensures knowledge integration. In contrast to traditional multi-task RL approaches that share knowledge through average return maximization, our meta learner incrementally integrates new experiences by explicitly minimizing catastrophic forgetting, thereby supporting efficient cumulative knowledge transfer for the fast learner. To facilitate rapid adaptation in new environments, we introduce an adaptive meta warm-up mechanism that selectively harnesses past knowledge. We conduct experiments in various pixel-based and continuous control benchmarks, revealing the superior performance of continual learning for our proposed dual-learner approach relative to baseline methods.

Dataset distillation aims to compress training data into fewer examples via a teacher, from which a student can learn effectively. While its success is often attributed to structure in the data, modern neural networks also memorize specific facts, but if and how such memorized information can be transferred in distillation settings remains less understood. While this transfer may be desirable in some applications, it also raises privacy concerns, where preventing such leakage is crucial. In this work, we show that students trained on soft labels from teachers can indeed achieve non-trivial accuracy on held-out memorized data they never directly observed. This effect persists on structured data when the teacher has not generalized. To understand this effect in isolation, we consider finite random i.i.d. datasets where generalization is a priori impossible and a successful teacher fit implies pure memorization. Still, students can learn non-trivial information about the held-out data, in some cases up to perfect accuracy. For multinomial logistic classification and single layer MLPs, we show this corresponds to the setting where the teacher can be recovered functionally -- the student matches the teacher's predictions on all possible inputs, including the held-out memorized data. We empirically show that these phenomena strongly depend on the sample complexity and the temperature with which the logits are smoothed, but persist across varying network capacities, architectures and dataset compositions.

Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input–output behavior allows the two models to be connected by a low-loss linear path. When such a path exists, the models are said to achieve linear mode connectivity (LMC). Prior studies, including Ainsworth et al., have reported that achieving LMC requires not only an appropriate permutation search but also sufficiently wide models (e.g., a 32 $\times$ width multiplier for ResNet-20). This is broadly believed to be because increasing the model width ensures a large enough space of candidate permutations, increasing the chance of finding one that yields LMC. In this work, we empirically demonstrate that, even without any permutations, simply widening the models is sufficient for achieving LMC when using a suitable softmax temperature calibration. We further explain why this phenomenon arises by analyzing intermediate layer outputs. Specifically, we introduce layerwise exponentially weighted connectivity (LEWC), which states that the output of each layer of the merged model can be represented as an exponentially weighted sum of the outputs of the corresponding layers of the original models. Consequently the merged model's output matches that of an ensemble of the original models, which facilitates LMC. To the best of our knowledge, this work is the first to show that widening the model not only facilitates nonlinear mode connectivity, as suggested in prior research, but also significantly increases the possibility of achieving linear mode connectivity.

Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond with “I don’t know”. Instead, they often produce incorrect answers while showing undue confidence, raising concerns about their factual reliability. In this work, we identify two pathological reasoning patterns characterized by overthinking that contribute to the overconfident and incorrect answers: last-minute guessing and second-thought spiraling. To address these issues, we propose BARREL—a novel framework that promotes concise and boundary-aware factual reasoning. Our experiments show that BARREL-training increases the reliability of DeepSeek-R1-Distill-Llama-8B from 39.33% to 61.48%, while still achieving accuracy comparable to models finetuned on reasoning data generated by R1. These results demonstrate that our pilot study is inspiring to build more reliable and factual System 2 LRMs.

Recent neural methods have shown promise in generalizing across various vehicle routing problems (VRPs). These methods adopt either a fully-shared dense model across all VRP tasks (i.e., variants) or a mixture-of-experts model that assigns node embeddings within each task instance to different experts. However, they both struggle to generalize from training tasks with basic constraints to out-of-distribution (OOD) tasks involving unseen constraint combinations and new basic constraints, as they overlook the fact that each VRP task is defined by a combination of multiple basic constraints. To address this, this paper proposes a novel model, combination-of-experts with knowledge sharing (CoEKS), which leverages the structural characteristic of VRP tasks. CoEKS enhances generalization to constraint combinations via two complementary components: a combination-of-experts architecture enabling flexible combinations via prior assignment of constraint-specific experts, and a knowledge sharing strategy strengthening generalization via automatic learning of transferable general knowledge across constraints. Moreover, CoEKS allows new experts to be plugged into the trained model for rapid adaptation to new constraints. Experiments demonstrate that CoEKS outperforms state-of-the-art methods on in-distribution tasks and delivers greater gains on OOD tasks, including unseen constraint combinations (relative improvement of 12\% over SOTA) and new constraints (25\% improvement).

Learning on large graphs presents significant challenges, with traditional Message Passing Neural Networks suffering from computational and memory costs scaling linearly with the number of edges. We introduce the Intersecting Block Graph (IBG), a low-rank factorization of large directed graphs based on combinations of intersecting bipartite components, each consisting of a pair of communities, for source and target nodes. By giving less weight to non-edges, we show how an IBG can efficiently approximate any graph, sparse or dense. Specifically, we prove a constructive version of the weak regularity lemma: for any chosen accuracy, every graph can be approximated by a dense IBG whose rank depends only on that accuracy. This improves over prior versions of the lemma, where the rank depended on the number of nodes for sparse graphs. Our method allows for efficient approximation of large graphs that are both directed and sparse, a crucial capability for many real-world applications. We then introduce a graph neural network architecture operating on the IBG representation of the graph and demonstrating competitive performance on node classification, spatio-temporal graph analysis, and knowledge graph completion, while having memory and computational complexity linear in the number of nodes rather than edges.

Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8× speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175× speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study.

Generalist Graph Anomaly Detection (GGAD) seeks a unified representation learning model to detect anomalies in unseen graphs, but cross-domain transfer often entangles the learned anomalous and normal representations. We formalize this degradation as Anomaly non-Discriminativity (AnD) and define a normalized score to quantify it. We present DR-GGAD, which avoids direct comparison between anomalous and normal nodes via two residual modules: 1) a multi-scale Hyper Residual (HR) Center measuring node-to-center distances, yielding a compact normal residual structure with margin-pushed anomalies; 2) an Affinity-Residual (AR) module enforcing local residual directional consistency to recover structural separability. With frozen parameters (no target fine-tuning), DR-GGAD fuses both signals into a unified score. On 8 benchmark target graphs, it achieves new SOTA: mean AUROC +5.14% over the best prior GGAD, with large gains on high-AnD datasets (Facebook +12.59%, ACM +9.96%, Amazon +7.48%) and strong AUPRC boosts (Amazon +17.12%, CiteSeer +17.77%). Ablations confirm complementary roles of the two modules. DR-GGAD thus establishes AnD as a measurable bottleneck and delivers robust cross-domain anomaly detection.

The inclusion of symmetries as an inductive bias, known as *equivariance*, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant architectures are usually highly constrained, designed for symmetries chosen *a priori*, and not applicable to datasets with other symmetries. This precludes the development of flexible, multi-modal foundation models capable of processing diverse data equivariantly. In this work, we build a single model --- the Any-Subgroup Equivariant Network (ASEN) --- that can be simultaneously equivariant to several groups, simply by modulating a certain auxiliary input feature. In particular, we start with a fully permutation-equivariant base model, and then obtain subgroup equivariance by using a symmetry-breaking input whose automorphism group is that subgroup. However, finding an input with the desired automorphism group is computationally hard. We overcome this by relaxing from exact to approximate symmetry breaking, leveraging the notion of 2-closure to derive fast algorithms. Theoretically, we show that our subgroup-equivariant networks can simulate equivariant MLPs, and their universality can be guaranteed if the base model is universal. Empirically, we validate our method on symmetry selection for graph and image tasks, as well as multitask and transfer learning for sequence tasks, showing that a single network equivariant to multiple permutation subgroups outperforms both separate equivariant models and a single non-equivariant model.

Human-aligned deep learning models exhibit behaviors consistent with human values, such as robustness, safety, and fairness. Transferring these behavioral properties to models trained on different tasks or data distributions remains challenging: aligned behavior is easily forgotten during fine-tuning, and collecting task-specific data that preserves this behavior can be prohibitively costly. We introduce BIRD, a flexible framework for transferring aligned behavior by matching the internal representation structure of a student model to that of a teacher. Applied to out-of-distribution robustness in image classification, BIRD outperforms fine-tuning, transfer learning, and continual learning methods, improving robust accuracy by up to 18\% over the next strongest baseline. It remains effective even when the teacher is trained on a much simpler dataset and is $25\times$ smaller in parameter count than the student. In a large-scale study of over 400 teacher-student pairs, we show that three interpretable and computable properties of the teacher's representations explain up to 85\% of the variance in transfer success, offering practical guidance for teacher selection and design. We further show that BIRD generalizes beyond applications in vision by enhancing safety alignment in language models when paired with Direct Preference Optimization and improving weak-to-strong generalization when combined with soft-label distillation. BIRD turns small, well-aligned models into scalable alignment seeds, mitigating challenges from key bottlenecks in deploying safe AI systems.

The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. In this work, we introduce a graph tokenization framework that generates sequential representations of graphs by combining reversible graph serialization, which preserves graph information, with Byte Pair Encoding (BPE), a widely adopted tokenizer in large language models (LLMs). To better capture structural information, the graph serialization process is guided by global statistics of graph substructures, ensuring that frequently occurring substructures appear more often in the sequence and can be merged by BPE into meaningful tokens. Empirical results demonstrate that the proposed tokenizer enables Transformers such as BERT to be directly applied to graph benchmarks without architectural modifications. The proposed approach achieves state-of-the-art results on 12 benchmark datasets and frequently outperforms both graph neural networks and specialized graph transformers. This work bridges the gap between graph-structured data and the ecosystem of sequence models.

When an LLM learns a new fact during finetuning (e.g., new movie releases, updated celebrity gossip, etc.), where does this information go? Are entities enriched with relation information, or do models recall information just-in-time before a prediction? Are ``all of the above'' true with LLMs implementing multiple redundant heuristics? Existing localization approaches (e.g., activation patching) are ill-suited for this analysis because they usually replace parts of the residual stream, thus overriding previous information. To fill this gap, we propose dynamic weight grafting, a technique that selectively grafts weights from a finetuned model onto a pretrained model. Using this technique, we show two separate pathways for retrieving finetuned relation information: 1) "enriching" the residual stream with relation information while processing the tokens that correspond to an entity (e.g., "Zendaya" in "Zendaya co-starred with John David Washington") and 2) "recalling" this information at the final token position before generating a target fact. In some cases, models need information from both of these pathways to correctly generate finetuned facts while, in other cases, either the "enrichment" or "recall" pathway alone is sufficient. We localize the "recall'' pathway to model components---finding that "recall" occurs via both task-specific attention mechanisms and an entity-specific extraction step in the feedforward networks of the final layers before the target prediction. By targeting model components and parameters, as opposed to just activations, we are able to understand the mechanisms by which finetuned knowledge is retrieved during generation.

Sheaf Neural Networks (SNNs) are a powerful algebraic-topology generalization of Graph Neural Networks (GNNs), and have been shown to significantly improve our ability to model complex relational data. While the GNN literature proved that incorporating directionality can substantially boost performance in many real-world applications, no SNNs approaches are known with such a capability. To address this limitation, we introduce the Directed Cellular Sheaf, a generalized cellular sheaf designed to explicitly account for edge orientations. Building on it, we define a corresponding sheaf Laplacian, the Directed Sheaf Laplacian $L^{\widetilde{\mathcal{F}}}$, which exploits the sheaf's structure to capture both the graph’s topology and its directions. $L^{\widetilde{\mathcal{F}}}$ serves as the backbone of the Directed Sheaf Neural Network (DSNN), the first SNN model to embed a directional bias into its architecture. Extensive experiments on twelve real-world benchmarks show that DSNN consistently outperforms many baseline methods.

Graph Neural Networks (GNNs) achieve strong predictive performance but offer limited transparency in their decision-making. Self-Interpretable GNNs (SI-GNNs) address this by generating built-in explanations, yet their training objectives are misaligned with evaluation criteria such as faithfulness. This raises two key questions: (i) can faithfulness be explicitly optimized during training, and (ii) does such optimization genuinely improve explanation quality? We show that faithfulness is intrinsically tied to explanation self-consistency and can therefore be optimized directly. Empirical analysis further reveals that self-inconsistency predominantly occurs on unimportant features, linking it to redundancy-driven explanation inconsistency observed in recent work and suggesting untapped potential for improving explanation quality. Building on these insights, we introduce a simple, model-agnostic self-consistency (SC) training strategy. Without changing architectures or pipelines, SC consistently improves explanation quality across multiple dimensions and benchmarks, offering an effective and scalable pathway to more trustworthy GNN explanations.