Singapore

GNN-to-MLP (G2M) methods have emerged as a promising approach to accelerate Graph Neural Networks (GNNs) by distilling their knowledge into simpler Multi-Layer Perceptrons (MLPs). These methods bridge the gap between the expressive power of GNNs and the computational efficiency of MLPs, making them well-suited for resource-constrained environments. However, existing G2M methods are limited by their inability to flexibly adjust inference cost and accuracy dynamically, a critical requirement for real-world applications where computational resources and time constraints can vary significantly. To address this, we introduce a Progressive framework designed to offer flexible and on-demand trade-offs between inference cost and accuracy for GNN-to-MLP knowledge distillation (ProGMLP). ProGMLP employs a Progressive Training Structure (PTS), where multiple MLP students are trained in sequence, each building on the previous one. Furthermore, ProGMLP incorporates Progressive Knowledge Distillation (PKD) to iteratively refine the distillation process from GNNs to MLPs, and Progressive Mixup Augmentation (PMA) to enhance generalization by progressively generating harder mixed samples. Our approach is validated through comprehensive experiments on eight real-world graph datasets, demonstrating that ProGMLP maintains high accuracy while dynamically adapting to varying runtime scenarios, making it highly effective for deployment in diverse application settings.

AAAI 2026

ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs

technical paper

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

This paper introduces the Shepherd Test, a new conceptual
test for assessing the moral and relational dimensions of
superintelligent artificial agents. The test is inspired by
human interactions with animals, where ethical
considerations about care, manipulation, and consumption
arise in contexts of asymmetric power and
self-preservation. We argue that AI crosses an important,
and potentially dangerous, threshold of intelligence when
it exhibits the ability to manipulate, nurture, and
instrumentally use less intelligent agents, while also
managing its own survival and expansion goals. This
includes the ability to weigh moral trade-offs between
self-interest and the well-being of subordinate agents. The
Shepherd Test thus challenges traditional AI evaluation
paradigms by emphasizing moral agency, hierarchical
behavior, and complex decision-making under existential
stakes. We argue that this shift is critical for advancing
AI governance, particularly as AI systems become
increasingly integrated into multi-agent environments. We
conclude by identifying key research directions, including
the development of simulation environments for testing
moral behavior in AI, and the formalization of ethical
manipulation within multi-agent systems.

The Shepherd Test: How Will Super Intelligent Agents Balance Care and Control in Asymmetric Relationships?

In multi-view classification tasks (MVC), each view provides an unique perspective on the data, offering complementary information that can improve classification performance when properly integrated. However, traditional methods typically adopt a uniform processing strategy for all views before fusion, overlooking the fact that different views may require different treatments due to variations in their quality and informativeness. 
To address this limitation, we propose a novel framework called Uncertainty-Guided View-Strength-Aware Feature Utilization (UVF) for multi-view classification. Our approach introduces a view uncertainty estimation module to quantify the discriminative strength of each view. Based on this estimation, a Differentiated Feature Selector (DFS) adaptively selects features, retaining informative dimensions in weak views while preserving original features in strong views. Furthermore, we employ an uncertainty-guided fusion strategy that assigns dynamic weights to each view's contribution based on its uncertainty score, enhancing the robustness and reliability of the final decision. Experimental results on benchmark datasets demonstrate that our method significantly outperforms conventional approaches, achieving better classification accuracy and interpretability through strength-aware feature processing and fusion.

Uncertainty-Guided View-Strength-Aware Feature Utilization for Multi-View Classification

The proliferation of complex, black-box AI models has intensified the need for techniques that can explain their decisions. Feature attribution methods have become a popular solution for providing post-hoc explanations, yet the field has historically lacked a formal problem definition. This paper addresses this gap by introducing a formal definition for the problem of feature attribution, which stipulates that explanations be supported by the given dataset representing an underlying probability distribution. Our analysis reveals that many existing model-agnostic methods fail to meet this criterion, while even those that do often possess other limitations. To overcome these challenges, we propose Distributional Feature Attribution eXplanations (DFAX), a novel, model-agnostic method for feature attribution. DFAX is the first to explain classifier predictions from a distributional perspective. We show through extensive experiments that DFAX is more effective and efficient than state-of-the-art baselines.

Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier

Multimodal large language models excel across diverse domains but struggle with complex visual reasoning tasks. To enhance their reasoning capabilities, current approaches typically rely on explicit search or post-training techniques. However, search-based methods suffer from computational inefficiency due to extensive solution space exploration, while post-training methods demand substantial data, computational resources, and often exhibit training instability. To address these challenges, we propose **AStar**, a training-free, **A**utomatic **S**tructured **t**hinking paradigm for multimod**a**l **r**easoning. Specifically, we introduce novel "thought cards", a lightweight library of high-level reasoning patterns abstracted from prior samples. For each test problem, AStar adaptively retrieves the optimal thought cards and seamlessly integrates these external explicit guidelines with the model’s internal implicit reasoning capabilities. Compared to previous methods, AStar eliminates computationally expensive explicit search and avoids additional complex post-training processes, enabling a more efficient reasoning approach. Extensive experiments demonstrate that our framework achieves 53.9% accuracy on MathVerse (surpassing GPT-4o's 50.2%) and 32.7% on MathVision (outperforming GPT-4o's 30.4%). Further analysis reveals the remarkable transferability of our method: thought cards generated from mathematical reasoning can also be applied to other reasoning tasks, even benefiting general visual perception and understanding. AStar serves as a plug-and-play test-time inference method, compatible with other post-training techniques, providing an important complement to existing multimodal reasoning approaches.

AStar: Boosting Multimodal Reasoning with Automated Structured Thinking

Text-prompted image segmentation enables fine-grained visual understanding and is critical for applications such as human-computer interaction and robotics. However, existing supervised fine-tuning methods typically ignore explicit chain-of-thought (CoT) reasoning at test time, which limits their ability to generalize to unseen prompts and domains. To address this issue, we introduce LENS, a scalable reinforcement-learning framework that jointly optimizes the reasoning process and segmentation in an end-to-end manner. We propose unified reinforcement-learning rewards that span sentence-, box-, and segment-level cues, encouraging the model to generate informative CoT rationales while refining mask quality. Using a publicly available 3-billion-parameter vision–language model, i.e., Qwen2.5-VL-3B-Instruct, LENS achieves an average cIoU of 81.2\% on the RefCOCO, RefCOCO+, and RefCOCOg benchmarks, outperforming the strong fine-tuned method, i.e., GLaMM, by up to 5.6\%. These results demonstrate that RL-driven CoT reasoning serves as a robust prior for text-prompted segmentation and offers a practical path toward more generalizable Segment Anything models.

LENS: Learning to Segment Anything with Unified Reinforced Reasoning

Offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL, promising safe and efficient knowledge acquisition by RL agents. However, OMRL still suffers extrapolation errors due to out-of-distribution (OOD) actions, compromised by broad task distributions and Markov Decision Process (MDP) ambiguity in meta-RL setups. Existing research indicates that the generalization of the $Q$ network affects the extrapolation error in offline RL. This paper investigates this relationship by decomposing the $Q$ value into feature and weight components, observing that while decomposition enhances adaptability and convergence in case of high-quality data, it often leads to policy degeneration or collapse in complex tasks. We observe that decomposed $Q$ values introduce a large estimation bias when the feature encounters OOD samples, a phenomenon we term "feature overgeneralization". To address this issue, we propose FLORA, which identifies OOD samples by modeling feature distributions and estimating their uncertainties. FLORA integrates a return feedback mechanism to adaptively adjust feature components. Furthermore, to learn precise task representations, FLORA explicitly models the complex task distribution using a chain of invertible transformations. We theoretically and empirically demonstrate that FLORA achieves rapid adaptation and meta-policy improvement compared to baselines across various environments.

Offline Meta-Reinforcement Learning with Flow-Based Task Inference and Adaptive Correction of Feature Overgeneralization

Tensor-based multi-view subspace clustering (MVSC) has achieved significant success by capturing high-order inter-view correlations. However, existing approaches face two principal limitations. First, most methods either exclusively emphasize the inter-view $\textbf{low‑rankness}$ (R) prior while neglecting the intra-view $\textbf{local-smoothness}$ (S) prior, or treat R and S as two separate regularizers—complicating joint optimization. Second, conventional $\textbf{tensor‑based}$ methods impose only low‑rank constraints on the representation tensor, which limits their ability to simultaneously model consistency and complementary information. To address these issues, we propose a $\textit{Unified View Extraction with Low‑Rankness and Smoothness Fusion (UVELRS)}$ method. Our framework first extracts a consistent cross‑view representation and then constructs a tensor by stacking these representations. We introduce a novel $\textit{tensor total variation Schatten p-norm}$ that simultaneously encodes both R and S priors while offering flexible singular‑value control. This unified formulation effectively captures both high-order inter-view correlations and intra-view local smoothness. Extensive experiments on real‑world datasets demonstrate UVELRS’s superior performance and robustness. We provide the source code of UVELRS in the supplementary material.

Unified View Extraction with Low-Rankness and Smoothness Fusion for Multi-View Subspace Clustering

Protein-Protein Interactions (PPIs) prediction is crucial for understanding cellular functions and disease mechanisms. Existing deep learning–based methods primarily rely on direct interaction within the PPI network to update protein representations. However, (1) such networks overlook the potential associations between functionally similar proteins, limiting the smoothing capability of Graph Neural Networks (GNNs) in learning representations for similar nodes. (2) Additionally, most approaches fail to adequately model the latent dependencies among interaction types (edge labels), which hinders their performance in PPI prediction tasks. To address these limitations, we propose SELC-PPI, a structure-enhanced and label correlation-aware model for protein-protein interactions prediction. Specifically, SELC-PPI first identifies similar proteins by leveraging both the topological information of the PPI network and the label distributions of nodes, constructing similarity edges. Then, it incorporates label co-occurrence statistics into the learning of label embeddings. Experimental results on multiple datasets and under various data split settings demonstrate that SELC-PPI significantly outperforms existing methods, validating the effectiveness of our model design.

Topology-Enhanced and Label Correlation-Aware Model for Protein-Protein Interaction Prediction

Recent progress in unsupervised probing methods, notably Contrast‑Consistent Search (CCS), has enabled the extraction of latent beliefs in language models without relying on token-level outputs. As these probes offer lightweight diagnostic tools with low alignment tax, a central question arises: can they effectively assess model alignment? We investigate this by examining CCS's sensitivity to harmful vs. safe statements and introducing Polarity‑Aware CCS (PA‑CCS), which evaluates whether a model's internal representations remain consistent under polarity inversion. We propose two alignment-oriented metrics—Polar‑Consistency and Contradiction Index—to quantify the semantic robustness of a model's latent knowledge. To validate PA-CCS, we curate two main and one control datasets containing matched harmful-safe sentence pairs formulated by different methods (concurrent and antagonistic statements), and apply PA-CCS to 18 language models. Our results demonstrate that PA‑CCS reveals both architectural and layer-specific differences in the encoding of latent harmful knowledge. Interestingly, replacing the negation token with a meaningless marker degrades the PA‑CCS scores of models with aligned representations. In contrast, models lacking robust internal calibration do not show this degradation. Our findings highlight the potential of unsupervised probing for alignment evaluation and call on the community to incorporate structural robustness checks into interpretability benchmarks.

Polarity-Aware Probing for Quantifying Latent Alignment in Language Models

Hamilton-Jacobi (HJ) reachability analysis provides a formal method for guaranteeing safety in constrained control problems. It synthesizes a value function to represent a long-term safe set called feasible region. Early synthesis methods based on state space discretization cannot scale to high-dimensional problems, while recent methods that use neural networks to approximate value functions result in unverifiable feasible regions. To achieve both scalability and verifiability, we propose a framework for synthesizing verified neural value functions for HJ reachability analysis. Our framework consists of three stages: pre-training, adversarial training, and verification-guided training. We design three techniques to address three challenges to improve scalability respectively: boundary-guided backtracking (BGB) to improve counterexample search efficiency, entering state regularization (ESR) to enlarge feasible region, and activation pattern alignment (APA) to accelerate neural network verification. We also provide a neural safety certificate synthesis and verification benchmark called Cersyve-9, which includes nine commonly used safe control tasks and supplements existing neural network verification benchmarks. Our framework successfully synthesizes verified neural value functions on all tasks, and our proposed three techniques exhibit superior scalability and efficiency compared with existing methods.

Downloads

Next from AAAI 2026

The Shepherd Test: How Will Super Intelligent Agents Balance Care and Control in Asymmetric Relationships?

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES