Ling Chen

Siyu Jiao, Gengwei Zhang, Shant Navasardyan et al. · gatech

In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level to obtain segmentation results. However, to obtain satisfactory segments, such a paradigm needs to couple the learning of the matching operations with heavy segmentation modules, limiting the flexibility of design and increasing the learning complexity. To alleviate this issue, we propose Mask Matching Transformer (MM-Former), a new paradigm for the few-shot segmentation task. Specifically, MM-Former first uses a class-agnostic segmenter to decompose the query image into multiple segment proposals. Then, a simple matching mechanism is applied to merge the related segment proposals into the final mask guided by the support images. The advantages of our MM-Former are two-fold. First, the MM-Former follows the paradigm of decompose first and then blend, allowing our method to benefit from the advanced potential objects segmenter to produce high-quality mask proposals for query images. Second, the mission of prototypical features is relaxed to learn coefficients to fuse correct ones within a proposal pool, making the MM-Former be well generalized to complex scenarios or cases. We conduct extensive experiments on the popular COCO-$20^i$ and Pascal-$5^i$ benchmarks. Competitive results well demonstrate the effectiveness and the generalization ability of our MM-Former.

Zihan Zhang, Meng Fang, Ling Chen et al.

Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment. Maintaining their up-to-date status is a pressing concern in the current era. This paper provides a comprehensive review of recent advances in aligning LLMs with the ever-changing world knowledge without re-training from scratch. We categorize research works systemically and provide in-depth comparisons and discussion. We also discuss existing challenges and highlight future directions to facilitate research in this field. We release the paper list at https://github.com/hyintell/awesome-refreshing-llms

Chen Ling, Xujiang Zhao, Xuchao Zhang et al.

Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks due to two key issues. First, LLMs struggle to distinguish irrelevant context from relevant relations and generate structured output due to the restrictions on fine-tuning the model. Second, LLMs generates responses autoregressively based on probability, which makes the predicted relations lack confidence. In this paper, we assess the capabilities of LLMs in improving the OIE task. Particularly, we propose various in-context learning strategies to enhance LLM's instruction-following ability and a demonstration uncertainty quantification module to enhance the confidence of the generated relations. Our experiments on three OIE benchmark datasets show that our approach holds its own against established supervised methods, both quantitatively and qualitatively.

Zihan Zhang, Meng Fang, Ling Chen et al.

Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics. However, with high-quality contextualized document representations, do we really need sophisticated neural models to obtain coherent and interpretable topics? In this paper, we conduct thorough experiments showing that directly clustering high-quality sentence embeddings with an appropriate word selecting method can generate more coherent and diverse topics than NTMs, achieving also higher efficiency and simplicity.

Pujan Paudel, Chen Ling, Jeremy Blackburn et al.

Images are a powerful and immediate vehicle to carry misleading or outright false messages, yet identifying image-based misinformation at scale poses unique challenges. In this paper, we present PIXELMOD, a system that leverages perceptual hashes, vector databases, and optical character recognition (OCR) to efficiently identify images that are candidates to receive soft moderation labels on Twitter. We show that PIXELMOD outperforms existing image similarity approaches when applied to soft moderation, with negligible performance overhead. We then test PIXELMOD on a dataset of tweets surrounding the 2020 US Presidential Election, and find that it is able to identify visually misleading images that are candidates for soft moderation with 0.99% false detection and 2.06% false negatives.

Xing Tang, Ling Chen

Temporal Knowledge Graph (TKG) representation learning embeds entities and event types into a continuous low-dimensional vector space by integrating the temporal information, which is essential for downstream tasks, e.g., event prediction and question answering. Existing methods stack multiple graph convolution layers to model the influence of distant entities, leading to the over-smoothing problem. To alleviate the problem, recent studies infuse reinforcement learning to obtain paths that contribute to modeling the influence of distant entities. However, due to the limited number of hops, these studies fail to capture the correlation between entities that are far apart and even unreachable. To this end, we propose GTRL, an entity Group-aware Temporal knowledge graph Representation Learning method. GTRL is the first work that incorporates the entity group modeling to capture the correlation between entities by stacking only a finite number of layers. Specifically, the entity group mapper is proposed to generate entity groups from entities in a learning way. Based on entity groups, the implicit correlation encoder is introduced to capture implicit correlations between any pairwise entity groups. In addition, the hierarchical GCNs are exploited to accomplish the message aggregation and representation updating on the entity group graph and the entity graph. Finally, GRUs are employed to capture the temporal dependency in TKGs. Extensive experiments on three real-world datasets demonstrate that GTRL achieves the state-of-the-art performances on the event prediction task, outperforming the best baseline by an average of 13.44%, 9.65%, 12.15%, and 15.12% in MRR, Hits@1, Hits@3, and Hits@10, respectively.

Chen Ling, Tanmoy Chowdhury, Junji Jiang et al.

Analogical reasoning is the process of discovering and mapping correspondences from a target subject to a base subject. As the most well-known computational method of analogical reasoning, Structure-Mapping Theory (SMT) abstracts both target and base subjects into relational graphs and forms the cognitive process of analogical reasoning by finding a corresponding subgraph (i.e., correspondence) in the target graph that is aligned with the base graph. However, incorporating deep learning for SMT is still under-explored due to several obstacles: 1) the combinatorial complexity of searching for the correspondence in the target graph; 2) the correspondence mining is restricted by various cognitive theory-driven constraints. To address both challenges, we propose a novel framework for Analogical Reasoning (DeepGAR) that identifies the correspondence between source and target domains by assuring cognitive theory-driven constraints. Specifically, we design a geometric constraint embedding space to induce subgraph relation from node embeddings for efficient subgraph search. Furthermore, we develop novel learning and optimization strategies that could end-to-end identify correspondences that are strictly consistent with constraints driven by the cognitive theory. Extensive experiments are conducted on synthetic and real-world datasets to demonstrate the effectiveness of the proposed DeepGAR over existing methods.

Guangji Bai, Chen Ling, Liang Zhao

Temporal domain generalization is a promising yet extremely challenging area where the goal is to learn models under temporally changing data distributions and generalize to unseen data distributions following the trends of the change. The advancement of this area is challenged by: 1) characterizing data distribution drift and its impacts on models, 2) expressiveness in tracking the model dynamics, and 3) theoretical guarantee on the performance. To address them, we propose a Temporal Domain Generalization with Drift-Aware Dynamic Neural Network (DRAIN) framework. Specifically, we formulate the problem into a Bayesian framework that jointly models the relation between data and model dynamics. We then build a recurrent graph generation scenario to characterize the dynamic graph-structured neural networks learned across different time points. It captures the temporal drift of model parameters and data distributions and can predict models in the future without the presence of future data. In addition, we explore theoretical guarantees of the model performance under the challenging temporal DG setting and provide theoretical analysis, including uncertainty and generalization error. Finally, extensive experiments on several real-world benchmarks with temporal drift demonstrate the effectiveness and efficiency of the proposed method.

Ling Chen, Chaodu Song, Xu Wang et al.

Anomaly detection based on system logs plays an important role in intelligent operations, which is a challenging task due to the extremely complex log patterns. Existing methods detect anomalies by capturing the sequential dependencies in log sequences, which ignore the interactions of subsequences. To this end, we propose CSCLog, a Component Subsequence Correlation-Aware Log anomaly detection method, which not only captures the sequential dependencies in subsequences, but also models the implicit correlations of subsequences. Specifically, subsequences are extracted from log sequences based on components and the sequential dependencies in subsequences are captured by Long Short-Term Memory Networks (LSTMs). An implicit correlation encoder is introduced to model the implicit correlations of subsequences adaptively. In addition, Graph Convolution Networks (GCNs) are employed to accomplish the information interactions of subsequences. Finally, attention mechanisms are exploited to fuse the embeddings of all subsequences. Extensive experiments on four publicly available log datasets demonstrate the effectiveness of CSCLog, outperforming the best baseline by an average of 7.41% in Macro F1-Measure.

Guangji Bai, Chen Ling, Yuyang Gao et al.

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful strategies against catastrophic forgetting. However, since forgetting is inevitable given bounded memory and unbounded tasks, how to forget is a problem continual learning must address. Therefore, beyond simply avoiding catastrophic forgetting, an under-explored issue is how to reasonably forget while ensuring the merits of human memory, including 1. storage efficiency, 2. generalizability, and 3. some interpretability. To achieve these simultaneously, our paper proposes a new saliency-augmented memory completion framework for continual learning, inspired by recent discoveries in memory completion separation in cognitive neuroscience. Specifically, we innovatively propose to store the part of the image most important to the tasks in episodic memory by saliency map extraction and memory encoding. When learning new tasks, previous data from memory are inpainted by an adaptive data generation module, which is inspired by how humans complete episodic memory. The module's parameters are shared across all tasks and it can be jointly trained with a continual learning classifier as bilevel optimization. Extensive experiments on several continual learning and image classification benchmarks demonstrate the proposed method's effectiveness and efficiency.

Binqing Wu, Weiqi Chen, Wengwei Wang et al.

Due to insufficient local area information, numerical weather prediction (NWP) may yield biases for specific areas. Previous studies correct biases mainly by employing handcrafted features or applying data-driven methods intuitively, overlooking the complicated dependencies between weather factors and between areas. To address this issue, we propose WeatherGNN, a local NWP bias-correction method that utilizes Graph Neural Networks (GNNs) to exploit meteorological dependencies and spatial dependencies under the guidance of domain knowledge. Specifically, we introduce a factor GNN to capture area-specific meteorological dependencies adaptively based on spatial heterogeneity and a fast hierarchical GNN to capture dynamic spatial dependencies efficiently guided by Tobler's first and second laws of geography. Our experimental results on two real-world datasets demonstrate that WeatherGNN achieves the state-of-the-art performance, outperforming the best baseline with an average of 4.75 \% on RMSE.

Rong Hu, Ling Chen, Shenghuan Miao et al.

In practice, Wearable Human Activity Recognition (WHAR) models usually face performance degradation on the new user due to user variance. Unsupervised domain adaptation (UDA) becomes the natural solution to cross-user WHAR under annotation scarcity. Existing UDA models usually align samples across domains without differentiation, which ignores the difference among samples. In this paper, we propose an unsupervised domain adaptation model with sample weight learning (SWL-Adapt) for cross-user WHAR. SWL-Adapt calculates sample weights according to the classification loss and domain discrimination loss of each sample with a parameterized network. We introduce the meta-optimization based update rule to learn this network end-to-end, which is guided by meta-classification loss on the selected pseudo-labeled target samples. Therefore, this network can fit a weighting function according to the cross-user WHAR task at hand, which is superior to existing sample differentiation rules fixed for special scenarios. Extensive experiments on three public WHAR datasets demonstrate that SWL-Adapt achieves the state-of-the-art performance on the cross-user WHAR task, outperforming the best baseline by an average of 3.1% and 5.3% in accuracy and macro F1 score, respectively.

Jun-En Ding, Chih-Ho Hsu, Kuan-Chia Ling et al.

The global COVID-19 pandemic has caused more than six million deaths worldwide. Medicalized hotels were established in Taiwan as quarantine facilities for COVID-19 patients with no or mild symptoms. Due to limited medical care available at these hotels, it is of paramount importance to identify patients at risk of clinical deterioration. This study aimed to develop and evaluate a graph-based deep learning approach for progressive hospital transfer risk prediction in a medicalized hotel setting. Vital sign measurements were obtained for 632 patients and daily patient similarity graphs were constructed. Inductive graph convolutional network models were trained on top of the temporally integrated graphs to predict hospital transfer risk. The proposed models achieved AUC scores above 0.83 for hospital transfer risk prediction based on the measurements of past 1, 2, and 3 days, outperforming baseline machine learning methods. A post-hoc analysis on the constructed diffusion-based graph using Local Clustering Coefficient discovered a high-risk cluster with significantly older mean age, higher body temperature, lower SpO2, and shorter length of stay. Further time-to-hospital-transfer survival analysis also revealed a significant decrease in survival probability in the discovered high-risk cluster. The obtained results demonstrated promising predictability and interpretability of the proposed graph-based approach. This technique may help preemptively detect high-risk patients at community-based medical facilities similar to a medicalized hotel.

Flavio Petruzzellis, Ling Xuan Chen, Alberto Testolin

Acquiring mathematical skills is considered a key challenge for modern Artificial Intelligence systems. Inspired by the way humans discover numerical knowledge, here we introduce a deep reinforcement learning framework that allows to simulate how cognitive agents could gradually learn to solve arithmetic problems by interacting with a virtual abacus. The proposed model successfully learn to perform multi-digit additions and subtractions, achieving an error rate below 1% even when operands are much longer than those observed during training. We also compare the performance of learning agents receiving a different amount of explicit supervision, and we analyze the most common error patterns to better understand the limitations and biases resulting from our design choices.

Chen Ling, Xujiang Zhao, Xuchao Zhang et al.

In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLM's response, such as hallucination, have also been actively discussed. Existing works have been devoted to quantifying the uncertainty in LLM's response, but they often overlook the complex nature of LLMs and the uniqueness of in-context learning. In this work, we delve into the predictive uncertainty of LLMs associated with in-context learning, highlighting that such uncertainties may stem from both the provided demonstrations (aleatoric uncertainty) and ambiguities tied to the model's configurations (epistemic uncertainty). We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion. Extensive experiments are conducted to demonstrate the effectiveness of the decomposition. The code and data are available at: https://github.com/lingchen0331/UQ_ICL.

Chen Ling, Xuchao Zhang, Xujiang Zhao et al.

Open-ended Commonsense Reasoning is defined as solving a commonsense question without providing 1) a short list of answer candidates and 2) a pre-defined answer scope. Conventional ways of formulating the commonsense question into a question-answering form or utilizing external knowledge to learn retrieval-based methods are less applicable in the open-ended setting due to an inherent challenge. Without pre-defining an answer scope or a few candidates, open-ended commonsense reasoning entails predicting answers by searching over an extremely large searching space. Moreover, most questions require implicit multi-hop reasoning, which presents even more challenges to our problem. In this work, we leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base, which does not require task-specific supervision. The reasoning paths can help to identify the most precise answer to the commonsense question. We conduct experiments on two commonsense benchmark datasets. Compared to other approaches, our proposed method achieves better performance both quantitatively and qualitatively.

Zongjiang Shang, Ling Chen, Binqing wu et al.

Although transformer-based methods have achieved great success in multi-scale temporal pattern interaction modeling, two key challenges limit their further development: (1) Individual time points contain less semantic information, and leveraging attention to model pair-wise interactions may cause the information utilization bottleneck. (2) Multiple inherent temporal variations (e.g., rising, falling, and fluctuating) entangled in temporal patterns. To this end, we propose Adaptive Multi-Scale Hypergraph Transformer (Ada-MSHyper) for time series forecasting. Specifically, an adaptive hypergraph learning module is designed to provide foundations for modeling group-wise interactions, then a multi-scale interaction module is introduced to promote more comprehensive pattern interactions at different scales. In addition, a node and hyperedge constraint mechanism is introduced to cluster nodes with similar semantic information and differentiate the temporal variations within each scales. Extensive experiments on 11 real-world datasets demonstrate that Ada-MSHyper achieves state-of-the-art performance, reducing prediction errors by an average of 4.56%, 10.38%, and 4.97% in MSE for long-range, short-range, and ultra-long-range time series forecasting, respectively. Code is available at https://github.com/shangzongjiang/Ada-MSHyper.

Wanqi Yang, Yanda Li, Meng Fang et al.

Adversarial audio attacks pose a significant threat to the growing use of large audio-language models (LALMs) in voice-based human-machine interactions. While existing research focused on model-specific adversarial methods, real-world applications demand a more generalizable and universal approach to audio adversarial attacks. In this paper, we introduce the Chat-Audio Attacks (CAA) benchmark including four distinct types of audio attacks, which aims to explore the vulnerabilities of LALMs to these audio attacks in conversational scenarios. To evaluate the robustness of LALMs, we propose three evaluation strategies: Standard Evaluation, utilizing traditional metrics to quantify model performance under attacks; GPT-4o-Based Evaluation, which simulates real-world conversational complexities; and Human Evaluation, offering insights into user perception and trust. We evaluate six state-of-the-art LALMs with voice interaction capabilities, including Gemini-1.5-Pro, GPT-4o, and others, using three distinct evaluation methods on the CAA benchmark. Our comprehensive analysis reveals the impact of four types of audio attacks on the performance of these models, demonstrating that GPT-4o exhibits the highest level of resilience. Our data can be accessed via the following link: \href{https://github.com/crystraldo/CAA}{CAA}.

Guangji Bai, Zheng Chai, Chen Ling et al.

The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI's ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges in the high consumption of computational, memory, energy, and financial resources, especially in environments with limited resource capabilities. This survey aims to systematically address these challenges by reviewing a broad spectrum of techniques designed to enhance the resource efficiency of LLMs. We categorize methods based on their optimization focus: computational, memory, energy, financial, and network resources and their applicability across various stages of an LLM's lifecycle, including architecture design, pretraining, finetuning, and system design. Additionally, the survey introduces a nuanced categorization of resource efficiency techniques by their specific resource types, which uncovers the intricate relationships and mappings between various resources and corresponding optimization techniques. A standardized set of evaluation metrics and datasets is also presented to facilitate consistent and fair comparisons across different models and techniques. By offering a comprehensive overview of the current sota and identifying open research avenues, this survey serves as a foundational reference for researchers and practitioners, aiding them in developing more sustainable and efficient LLMs in a rapidly evolving landscape.

Zijing Shi, Meng Fang, Shunfeng Zheng et al.

Multi-agent collaboration with Large Language Models (LLMs) demonstrates proficiency in basic tasks, yet its efficiency in more complex scenarios remains unexplored. In gaming environments, these agents often face situations without established coordination protocols, requiring them to make intelligent inferences about teammates from limited data. This problem motivates the area of ad hoc teamwork, in which an agent may potentially cooperate with a variety of teammates to achieve a shared goal. Our study focuses on the ad hoc teamwork problem where the agent operates in an environment driven by natural language. Our findings reveal the potential of LLM agents in team collaboration, highlighting issues related to hallucinations in communication. To address this issue, we develop CodeAct, a general agent that equips LLM with enhanced memory and code-driven reasoning, enabling the repurposing of partial information for rapid adaptation to new teammates.

Zongjiang Shang, Ling Chen, Binqing Wu et al.

Demystifying interactions between temporal patterns of different scales is fundamental to precise long-range time series forecasting. However, previous works lack the ability to model high-order interactions. To promote more comprehensive pattern interaction modeling for long-range time series forecasting, we propose a Multi-Scale Hypergraph Transformer (MSHyper) framework. Specifically, a multi-scale hypergraph is introduced to provide foundations for modeling high-order pattern interactions. Then by treating hyperedges as nodes, we also build a hyperedge graph to enhance hypergraph modeling. In addition, a tri-stage message passing mechanism is introduced to aggregate pattern information and learn the interaction strength between temporal patterns of different scales. Extensive experiments on five real-world datasets demonstrate that MSHyper achieves state-of-the-art (SOTA) performance across various settings.

Wanqi Yang, Yanda Li, Yunchao Wei et al.

Large audio-language models (LALMs) have achieved near-human performance in sentence-level transcription and emotion recognition. However, existing evaluations focus mainly on surface-level perception, leaving the capacity of models for contextual and inference-driven reasoning in speech-based scenarios insufficiently examined. To address this gap, we introduce SpeechR, a unified benchmark for evaluating reasoning over speech in large audio-language models. SpeechR evaluates models along three key dimensions: factual retrieval, procedural inference, and normative judgment. It includes three distinct evaluation formats. The multiple-choice version measures answer selection accuracy. The generative version assesses the coherence and logical consistency of reasoning chains. The acoustic-feature version investigates whether variations in stress and emotion affect reasoning performance. Evaluations on eleven state-of-the-art LALMs reveal that high transcription accuracy does not translate into strong reasoning capabilities. SpeechR establishes a structured benchmark for evaluating reasoning in spoken language, enabling more targeted analysis of model capabilities across diverse dialogue-based tasks.

Beibei Yu, Tao Shen, Hongbin Na et al.

Remote-sensing mineral exploration is critical for identifying economically viable mineral deposits, yet it poses significant challenges for multimodal large language models (MLLMs). These include limitations in domain-specific geological knowledge and difficulties in reasoning across multiple remote-sensing images, further exacerbating long-context issues. To address these, we present MineAgent, a modular framework leveraging hierarchical judging and decision-making modules to improve multi-image reasoning and spatial-spectral integration. Complementing this, we propose MineBench, a benchmark specific for evaluating MLLMs in domain-specific mineral exploration tasks using geological and hyperspectral data. Extensive experiments demonstrate the effectiveness of MineAgent, highlighting its potential to advance MLLMs in remote-sensing mineral exploration.

Ling Chen, Jiahua Cui

Time series refer to a series of data points indexed in time order, which can be found in various fields, e.g., transportation, healthcare, and finance. Accurate time series forecasting can enhance optimization planning and decision-making support. Time series have multi-scale characteristics, i.e., different temporal patterns at different scales, which presents a challenge for time series forecasting. In this paper, we propose TPRNN, a Top-down Pyramidal Recurrent Neural Network for time series forecasting. We first construct subsequences of different scales from the input, forming a pyramid structure. Then by executing a multi-scale information interaction module from top to bottom, we model both the temporal dependencies of each scale and the influences of subsequences of different scales, resulting in a complete modeling of multi-scale temporal patterns in time series. Experiments on seven real-world datasets demonstrate that TPRNN has achieved the state-of-the-art performance with an average improvement of 8.13% in MSE compared to the best baseline.

Rongrong Ma, Guansong Pang, Ling Chen

Graph neural networks (GNNs) have achieved state-of-the-art performance in graph representation learning. Message passing neural networks, which learn representations through recursively aggregating information from each node and its neighbors, are among the most commonly-used GNNs. However, a wealth of structural information of individual nodes and full graphs is often ignored in such process, which restricts the expressive power of GNNs. Various graph data augmentation methods that enable the message passing with richer structure knowledge have been introduced as one main way to tackle this issue, but they are often focused on individual structure features and difficult to scale up with more structure features. In this work we propose a novel approach, namely collective structure knowledge-augmented graph neural network (CoS-GNN), in which a new message passing method is introduced to allow GNNs to harness a diverse set of node- and graph-level structure features, together with original node features/attributes, in augmented graphs. In doing so, our approach largely improves the structural knowledge modeling of GNNs in both node and graph levels, resulting in substantially improved graph representations. This is justified by extensive empirical results where CoS-GNN outperforms state-of-the-art models in various graph-level learning tasks, including graph classification, anomaly detection, and out-of-distribution generalization.

Yi Rong, Yingchi Mao, Yinqiu Liu et al.

Traffic speed prediction is significant for intelligent navigation and congestion alleviation. However, making accurate predictions is challenging due to three factors: 1) traffic diffusion, i.e., the spatial and temporal causality existing between the traffic conditions of multiple neighboring roads, 2) the poor interpretability of traffic data with complicated spatio-temporal correlations, and 3) the latent pattern of traffic speed fluctuations over time, such as morning and evening rush. Jointly considering these factors, in this paper, we present a novel architecture for traffic speed prediction, called Interpretable Causal Spatio-Temporal Diffusion Network (ICST-DNET). Specifically, ICST-DENT consists of three parts, namely the Spatio-Temporal Causality Learning (STCL), Causal Graph Generation (CGG), and Speed Fluctuation Pattern Recognition (SFPR) modules. First, to model the traffic diffusion within road networks, an STCL module is proposed to capture both the temporal causality on each individual road and the spatial causality in each road pair. The CGG module is then developed based on STCL to enhance the interpretability of the traffic diffusion procedure from the temporal and spatial perspectives. Specifically, a time causality matrix is generated to explain the temporal causality between each road's historical and future traffic conditions. For spatial causality, we utilize causal graphs to visualize the diffusion process in road pairs. Finally, to adapt to traffic speed fluctuations in different scenarios, we design a personalized SFPR module to select the historical timesteps with strong influences for learning the pattern of traffic speed fluctuations. Extensive experimental results prove that ICST-DNET can outperform all existing baselines, as evidenced by the higher prediction accuracy, ability to explain causality, and adaptability to different scenarios.

Shunfeng Zheng, Yudi Zhang, Meng Fang et al.

Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning-such as solving Olympiad-level physics problems-remains largely unexplored. Inspired by the way students prepare for competitions by reviewing past problems, we investigate the potential of RAG to enhance physics reasoning in foundation models. We introduce PhoPile, a high-quality multimodal dataset specifically designed for Olympiad-level physics, enabling systematic study of retrieval-based reasoning. PhoPile includes diagrams, graphs, and equations, capturing the inherently multimodal nature of physics problem solving. Using PhoPile, we benchmark RAG-augmented foundation models, covering both large language models (LLMs) and large multimodal models (LMMs) with multiple retrievers. Our results demonstrate that integrating retrieval with physics corpora can improve model performance, while also highlighting challenges that motivate further research in retrieval-augmented physics reasoning.

Yuxi Lu, Biao Wu, Zhidong Li et al.

World models have shown potential in artificial intelligence by predicting and reasoning about world states beyond direct observations. However, existing approaches are predominantly evaluated in synthetic environments or constrained scene settings, limiting their validation in real-world contexts with broad spatial coverage and complex semantics. Meanwhile, remote sensing applications urgently require spatial reasoning capabilities for disaster response and urban planning. This paper bridges these gaps by introducing the first framework for world modeling in remote sensing. We formulate remote sensing world modeling as direction-conditioned spatial extrapolation, where models generate semantically consistent adjacent image tiles given a central observation and directional instruction. To enable rigorous evaluation, we develop RSWISE (Remote Sensing World-Image Spatial Evaluation), a benchmark containing 1,600 evaluation tasks across four scenarios: general, flood, urban, and rural. RSWISE combines visual fidelity assessment with instruction compliance evaluation using GPT-4o as a semantic judge, ensuring models genuinely perform spatial reasoning rather than simple replication. Afterwards, we present RemoteBAGEL, a unified multimodal model fine-tuned on remote sensing data for spatial extrapolation tasks. Extensive experiments demonstrate that RemoteBAGEL consistently outperforms state-of-the-art baselines on RSWISE.

Binqing Wu, Jianlong Huang, Zongjiang Shang et al.

In multivariate time series (MTS) forecasting, many deep learning based methods have been proposed for modeling dependencies at multiple spatial (inter-variate) or temporal (intra-variate) scales. However, existing methods may fail to model dependencies across multiple spatial-temporal scales (ST-scales, i.e., scales that jointly consider spatial and temporal scopes). In this work, we propose ST-Hyper to model the high-order dependencies across multiple ST-scales through adaptive hypergraph modeling. Specifically, we introduce a Spatial-Temporal Pyramid Modeling (STPM) module to extract features at multiple ST-scales. Furthermore, we introduce an Adaptive Hypergraph Modeling (AHM) module that learns a sparse hypergraph to capture robust high-order dependencies among features. In addition, we interact with these features through tri-phase hypergraph propagation, which can comprehensively capture multi-scale spatial-temporal dynamics. Experimental results on six real-world MTS datasets demonstrate that ST-Hyper achieves the state-of-the-art performance, outperforming the best baselines with an average MAE reduction of 3.8\% and 6.8\% for long-term and short-term forecasting, respectively.

Zihao Sun, Ling Chen

Recent progress in large language models (LLMs) has enabled the development of autonomous web agents capable of navigating and interacting with real websites. However, evaluating such agents remains challenging due to the instability and inconsistency of existing benchmarks, which often rely on dynamic content or oversimplified simulations. In this work, we introduce WebArXiv, a static and time-invariant benchmark comprising 275 web-based tasks grounded in the arXiv platform. WebArXiv ensures reproducible and reliable evaluation by anchoring tasks in fixed web snapshots with deterministic ground truths and standardized action trajectories. Through behavioral analysis, we identify a common failure mode, Rigid History Reflection, where agents over-rely on fixed interaction histories. To address this, we propose a lightweight dynamic reflection mechanism that allows agents to selectively retrieve relevant past steps during decision-making. We evaluate ten state-of-the-art web agents on WebArXiv. Results demonstrate clear performance differences across agents and validate the effectiveness of our proposed reflection strategy.

Qian Chen, Ling Chen

Temporal Knowledge Graph (TKG) representation learning aims to map temporal evolving entities and relations to embedded representations in a continuous low-dimensional vector space. However, existing approaches cannot capture the temporal evolution of high-order correlations in TKGs. To this end, we propose a Deep Evolutionary Clustering jointed temporal knowledge graph Representation Learning approach (DECRL). Specifically, a deep evolutionary clustering module is proposed to capture the temporal evolution of high-order correlations among entities. Furthermore, a cluster-aware unsupervised alignment mechanism is introduced to ensure the precise one-to-one alignment of soft overlapping clusters across timestamps, thereby maintaining the temporal smoothness of clusters. In addition, an implicit correlation encoder is introduced to capture latent correlations between any pair of clusters under the guidance of a global graph. Extensive experiments on seven real-world datasets demonstrate that DECRL achieves the state-of-the-art performances, outperforming the best baseline by an average of 9.53%, 12.98%, 10.42%, and 14.68% in MRR, Hits@1, Hits@3, and Hits@10, respectively.

Xin Zhang, Ling Chen, Xing Tang et al.

Air quality estimation can provide air quality for target regions without air quality stations, which is useful for the public. Existing air quality estimation methods divide the study area into disjointed grid regions, and apply 2D convolution to model the spatial dependencies of adjacent grid regions based on the first law of geography, failing to model the spatial dependencies of distant grid regions. To this end, we propose a Dual-view Supergrid-aware Graph Neural Network (DSGNN) for regional air quality estimation, which can model the spatial dependencies of distant grid regions from dual views (i.e., satellite-derived aerosol optical depth (AOD) and meteorology). Specifically, images are utilized to represent the regional data (i.e., AOD data and meteorology data). The dual-view supergrid learning module is introduced to generate supergrids in a parameterized way. Based on the dual-view supergrids, the dual-view implicit correlation encoding module is introduced to learn the correlations between pairwise supergrids. In addition, the dual-view message passing network is introduced to implement the information interaction on the supergrid graphs and images. Extensive experiments on two real-world datasets demonstrate that DSGNN achieves the state-of-the-art performances on the air quality estimation task, outperforming the best baseline by an average of 19.64% in MAE.

Jiajia Wu, Ling Chen

As a crucial technique for developing a smart city, traffic forecasting has become a popular research focus in academic and industrial communities for decades. This task is highly challenging due to complex and dynamic spatial-temporal dependencies in traffic networks. Existing works ignore continuous temporal dependencies and spatial dependencies evolving over time. In this paper, we propose Continuously Evolving Graph Neural Controlled Differential Equations (CEGNCDE) to capture continuous temporal dependencies and spatial dependencies over time simultaneously. Specifically, a continuously evolving graph generator (CEGG) based on NCDE is introduced to generate the spatial dependencies graph that continuously evolves over time from discrete historical observations. Then, a graph neural controlled differential equations (GNCDE) framework is introduced to capture continuous temporal dependencies and spatial dependencies over time simultaneously. Extensive experiments demonstrate that CEGNCDE outperforms the SOTA methods by average 2.34% relative MAE reduction, 0.97% relative RMSE reduction, and 3.17% relative MAPE reduction.

Pengyue Jia, Ling Chen, Dandan Lyu

Predicting the number of infections in the anti-epidemic process is extremely beneficial to the government in developing anti-epidemic strategies, especially in fine-grained geographic units. Previous works focus on low spatial resolution prediction, e.g., county-level, and preprocess data to the same geographic level, which loses some useful information. In this paper, we propose a fine-grained population mobility data-based model (FGC-COVID) utilizing data of two geographic levels for community-level COVID-19 prediction. We use the population mobility data between Census Block Groups (CBGs), which is a finer-grained geographic level than community, to build the graph and capture the dependencies between CBGs using graph neural networks (GNNs). To mine as finer-grained patterns as possible for prediction, a spatial weighted aggregation module is introduced to aggregate the embeddings of CBGs to community level based on their geographic affiliation and spatial autocorrelation. Extensive experiments on 300 days LA city COVID-19 data indicate our model outperforms existing forecasting models on community-level COVID-19 prediction.

Yayong Li, Jie Yin, Ling Chen

Graph Neural Networks (GNNs) have achieved state-of-the-art results for semi-supervised node classification on graphs. Nevertheless, the challenge of how to effectively learn GNNs with very few labels is still under-explored. As one of the prevalent semi-supervised methods, pseudo-labeling has been proposed to explicitly address the label scarcity problem. It aims to augment the training set with pseudo-labeled unlabeled nodes with high confidence so as to re-train a supervised model in a self-training cycle. However, the existing pseudo-labeling approaches often suffer from two major drawbacks. First, they tend to conservatively expand the label set by selecting only high-confidence unlabeled nodes without assessing their informativeness. Unfortunately, those high-confidence nodes often convey overlapping information with given labels, leading to minor improvements for model re-training. Second, these methods incorporate pseudo-labels to the same loss function with genuine labels, ignoring their distinct contributions to the classification task. In this paper, we propose a novel informative pseudo-labeling framework, called InfoGNN, to facilitate learning of GNNs with extremely few labels. Our key idea is to pseudo label the most informative nodes that can maximally represent the local neighborhoods via mutual information maximization. To mitigate the potential label noise and class-imbalance problem arising from pseudo labeling, we also carefully devise a generalized cross entropy loss with a class-balanced regularization to incorporate generated pseudo labels into model re-training. Extensive experiments on six real-world graph datasets demonstrate that our proposed approach significantly outperforms state-of-the-art baselines and strong self-supervised methods on graphs.

Ling Chen, Miaomiao Dong

Nowadays, different types of context information are integrated into mobile messaging to increase expressiveness and awareness, including mobile device setting, location, activity, and heart rate. Due to low recognition accuracy, sometimes users cannot accurately infer others' status through activity awareness. Recently, activity recognition technology has advanced. However, the user behaviors of activity awareness with improved technology have not been studied. In this study, we design ActAware, a mobile instant messaging application that integrates activity awareness based on improved activity recognition technology, i.e., improved recognition accuracy and the addition of activity transition notification. We conduct a field study to explore user behaviors and found that activity awareness allows users to speculate on the reasons for chat interruption, plan communication, speculate on whether the chat partner is departing/arriving, and deepen the understanding of living patterns. Compared with disclosing other types of context information, users have fewer privacy concerns about disclosing activity information in ActAware. Based on these findings, we provide design recommendations for mobile messaging to better support activity awareness.

Ling Chen, Donghui Chen, Zongjiang Shang et al.

Multivariate time series (MTS) forecasting plays an important role in the automation and optimization of intelligent applications. It is a challenging task, as we need to consider both complex intra-variable dependencies and inter-variable dependencies. Existing works only learn temporal patterns with the help of single inter-variable dependencies. However, there are multi-scale temporal patterns in many real-world MTS. Single inter-variable dependencies make the model prefer to learn one type of prominent and shared temporal patterns. In this paper, we propose a multi-scale adaptive graph neural network (MAGNN) to address the above issue. MAGNN exploits a multi-scale pyramid network to preserve the underlying temporal dependencies at different time scales. Since the inter-variable dependencies may be different under distinct time scales, an adaptive graph learning module is designed to infer the scale-specific inter-variable dependencies without pre-defined priors. Given the multi-scale feature representations and scale-specific inter-variable dependencies, a multi-scale temporal graph neural network is introduced to jointly model intra-variable dependencies and inter-variable dependencies. After that, we develop a scale-wise fusion module to effectively promote the collaboration across different time scales, and automatically capture the importance of contributed temporal patterns. Experiments on four real-world datasets demonstrate that MAGNN outperforms the state-of-the-art methods across various settings.

Donghui Chen, Ling Chen, Zongjiang Shang et al.

Multivariate time series (MTS) forecasting has attracted much attention in many intelligent applications. It is not a trivial task, as we need to consider both intra-variable dependencies and inter-variable dependencies. However, existing works are designed for specific scenarios, and require much domain knowledge and expert efforts, which is difficult to transfer between different scenarios. In this paper, we propose a scale-aware neural architecture search framework for MTS forecasting (SNAS4MTF). A multi-scale decomposition module transforms raw time series into multi-scale sub-series, which can preserve multi-scale temporal patterns. An adaptive graph learning module infers the different inter-variable dependencies under different time scales without any prior knowledge. For MTS forecasting, a search space is designed to capture both intra-variable dependencies and inter-variable dependencies at each time scale. The multi-scale decomposition, adaptive graph learning, and neural architecture search modules are jointly learned in an end-to-end framework. Extensive experiments on two real-world datasets demonstrate that SNAS4MTF achieves a promising performance compared with the state-of-the-art methods.

Ling Chen, Weiqi Chen, Binqing Wu et al.

Time series forecasting is a significant problem in many applications, e.g., financial predictions and business optimization. Modern datasets can have multiple correlated time series, which are often generated with global (shared) regularities and local (specific) dynamics. In this paper, we seek to tackle such forecasting problems with DeepDGL, a deep forecasting model that disentangles dynamics into global and local temporal patterns. DeepDGL employs an encoder-decoder architecture, consisting of two encoders to learn global and local temporal patterns, respectively, and a decoder to make multi-step forecasting. Specifically, to model complicated global patterns, the vector quantization (VQ) module is introduced, allowing the global feature encoder to learn a shared codebook among all time series. To model diversified and heterogenous local patterns, an adaptive parameter generation module enhanced by the contrastive multi-horizon coding (CMC) is proposed to generate the parameters of the local feature encoder for each individual time series, which maximizes the mutual information between the series-specific context variable and the long/short-term representations of the corresponding time series. Our experiments on several real-world datasets show that DeepDGL outperforms existing state-of-the-art models.

Ling Chen, Jun Cui, Xing Tang et al.

Although the state-of-the-art traditional representation learning (TRL) models show competitive performance on knowledge graph completion, there is no parameter sharing between the embeddings of entities, and the connections between entities are weak. Therefore, neighbor aggregation-based representation learning (NARL) models are proposed, which encode the information in the neighbors of an entity into its embeddings. However, existing NARL models either only utilize one-hop neighbors, ignoring the information in multi-hop neighbors, or utilize multi-hop neighbors by hierarchical neighbor aggregation, destroying the completeness of multi-hop neighbors. In this paper, we propose a NARL model named RMNA, which obtains and filters horn rules through a rule mining algorithm, and uses selected horn rules to transform valuable multi-hop neighbors into one-hop neighbors, therefore, the information in valuable multi-hop neighbors can be completely utilized by aggregating these one-hop neighbors. In experiments, we compare RMNA with the state-of-the-art TRL models and NARL models. The results show that RMNA has a competitive performance.

Ling Chen, Shanshan Yu, Dandan Lyu et al.

Temporal interaction networks are formed in many fields, e.g., e-commerce, online education, and social network service. Temporal interaction network embedding can effectively mine the information in temporal interaction networks, which is of great significance to the above fields. Usually, the occurrence of an interaction affects not only the nodes directly involved in the interaction (interacting nodes), but also the neighbor nodes of interacting nodes. However, existing temporal interaction network embedding methods only use historical interaction relations to mine neighbor nodes, ignoring other relation types. In this paper, we propose a multi-relation aware temporal interaction network embedding method (MRATE). Based on historical interactions, MRATE mines historical interaction relations, common interaction relations, and interaction sequence similarity relations to obtain the neighbor based embeddings of interacting nodes. The hierarchical multi-relation aware aggregation method in MRATE first employs graph attention networks (GATs) to aggregate the interaction impacts propagated through a same relation type and then combines the aggregated interaction impacts from multiple relation types through the self-attention mechanism. Experiments are conducted on three public temporal interaction network datasets, and the experimental results show the effectiveness of MRATE.

Ling Chen, Jiahui Xu, Binqing Wu et al.

The problem of air pollution threatens public health. Air quality forecasting can provide the air quality index hours or even days later, which can help the public to prevent air pollution in advance. Previous works focus on citywide air quality forecasting and cannot solve nationwide city forecasting problem, whose difficulties lie in capturing the latent dependencies between geographically distant but highly correlated cities. In this paper, we propose the group-aware graph neural network (GAGNN), a hierarchical model for nationwide city air quality forecasting. The model constructs a city graph and a city group graph to model the spatial and latent dependencies between cities, respectively. GAGNN introduces differentiable grouping network to discover the latent dependencies among cities and generate city groups. Based on the generated city groups, a group correlation encoding module is introduced to learn the correlations between them, which can effectively capture the dependencies between city groups. After the graph construction, GAGNN implements message passing mechanism to model the dependencies between cities and city groups. The evaluation experiments on Chinese city air quality dataset indicate that our GAGNN outperforms existing forecasting models.

Ling Chen, Yi Zhang, Shenghuan Miao et al.

Unsupervised user adaptation aligns the feature distributions of the data from training users and the new user, so a well-trained wearable human activity recognition (WHAR) model can be well adapted to the new user. With the development of wearable sensors, multiple wearable sensors based WHAR is gaining more and more attention. In order to address the challenge that the transferabilities of different sensors are different, we propose SALIENCE (unsupervised user adaptation model for multiple wearable sensors based human activity recognition) model. It aligns the data of each sensor separately to achieve local alignment, while uniformly aligning the data of all sensors to ensure global alignment. In addition, an attention mechanism is proposed to focus the activity classifier of SALIENCE on the sensors with strong feature discrimination and well distribution alignment. Experiments are conducted on two public WHAR datasets, and the experimental results show that our model can yield a competitive performance.

Ling Chen, Hongyu Shi

Predicting user positive response (e.g., purchases and clicks) probability is a critical task in Web applications. To identify predictive features from raw data, the state-of-the-art extreme deep factorization machine model (xDeepFM) introduces a new interaction network to leverage feature interactions at the vector-wise level explicitly. However, since each hidden layer in the interaction network is a collection of feature maps, it can be viewed essentially as an ensemble of different feature maps. In this case, only using a single objective to minimize the prediction loss may lead to overfitting and generate correlated errors. In this paper, an ensemble diversity enhanced extreme deep factorization machine model (DexDeepFM) is proposed, which designs the ensemble diversity measure in each hidden layer and considers both ensemble diversity and prediction accuracy in the objective function. In addition, the attention mechanism is introduced to discriminate the importance of ensemble diversity measures with different feature interaction orders. Extensive experiments on three public real-world datasets are conducted to show the effectiveness of the proposed model.

Wei Huang, Yayong Li, Weitao Du et al.

Graph convolutional networks (GCNs) and their variants have achieved great success in dealing with graph-structured data. Nevertheless, it is well known that deep GCNs suffer from the over-smoothing problem, where node representations tend to be indistinguishable as more layers are stacked up. The theoretical research to date on deep GCNs has focused primarily on expressive power rather than trainability, an optimization perspective. Compared to expressivity, trainability attempts to address a more fundamental question: Given a sufficiently expressive space of models, can we successfully find a good solution via gradient descent-based optimizers? This work fills this gap by exploiting the Graph Neural Tangent Kernel (GNTK), which governs the optimization trajectory under gradient descent for wide GCNs. We formulate the asymptotic behaviors of GNTK in the large depth, which enables us to reveal the dropping trainability of wide and deep GCNs at an exponential rate in the optimization process. Additionally, we extend our theoretical framework to analyze residual connection-based techniques, which are found to be merely able to mitigate the exponential decay of trainability mildly. Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally. Experimental evaluation consistently confirms using our proposed method can achieve better results compared to relevant counterparts with both infinite-width and finite-width.

Jiahui Xu, Ling Chen, Mingqi Lv et al.

Accurately forecasting air quality is critical to protecting general public from lung and heart diseases. This is a challenging task due to the complicated interactions among distinct pollution sources and various other influencing factors. Existing air quality forecasting methods cannot effectively model the diffusion processes of air pollutants between cities and monitoring stations, which may suddenly deteriorate the air quality of a region. In this paper, we propose HighAir, i.e., a hierarchical graph neural network-based air quality forecasting method, which adopts an encoder-decoder architecture and considers complex air quality influencing factors, e.g., weather and land usage. Specifically, we construct a city-level graph and station-level graphs from a hierarchical perspective, which can consider city-level and station-level patterns, respectively. We design two strategies, i.e., upper delivery and lower updating, to implement the inter-level interactions, and introduce message passing mechanism to implement the intra-level interactions. We dynamically adjust edge weights based on wind direction to model the correlations between dynamic factors and air quality. We compare HighAir with the state-of-the-art air quality forecasting methods on the dataset of Yangtze River Delta city group, which covers 10 major cities within 61,500 km2. The experimental results show that HighAir significantly outperforms other methods.

Yunqiu Xu, Meng Fang, Ling Chen et al.

We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language. While different methods have been developed to represent the environment information and language actions, existing RL agents are not empowered with any reasoning capabilities to deal with textual games. In this work, we aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We propose a stacked hierarchical attention mechanism to construct an explicit representation of the reasoning process by exploiting the structure of the knowledge graph. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.

Xuhui Fan, Yaqiong Li, Ling Chen et al.

Modelling exchangeable relational data can be described by \textit{graphon theory}. Most Bayesian methods for modelling exchangeable relational data can be attributed to this framework by exploiting different forms of graphons. However, the graphons adopted by existing Bayesian methods are either piecewise-constant functions, which are insufficiently flexible for accurate modelling of the relational data, or are complicated continuous functions, which incur heavy computational costs for inference. In this work, we introduce a smoothing procedure to piecewise-constant graphons to form {\em smoothing graphons}, which permit continuous intensity values for describing relations, but without impractically increasing computational costs. In particular, we focus on the Bayesian Stochastic Block Model (SBM) and demonstrate how to adapt the piecewise-constant SBM graphon to the smoothed version. We initially propose the Integrated Smoothing Graphon (ISG) which introduces one smoothing parameter to the SBM graphon to generate continuous relational intensity values. We then develop the Latent Feature Smoothing Graphon (LFSG), which improves on the ISG by introducing auxiliary hidden labels to decompose the calculation of the ISG intensity and enable efficient inference. Experimental results on real-world data sets validate the advantages of applying smoothing strategies to the Stochastic Block Model, demonstrating that smoothing graphons can greatly improve AUC and precision for link prediction without increasing computational complexity.

Yaqiong Li, Xuhui Fan, Ling Chen et al.

The Dirichlet Belief Network~(DirBN) has been recently proposed as a promising approach in learning interpretable deep latent representations for objects. In this work, we leverage its interpretable modelling architecture and propose a deep dynamic probabilistic framework -- the Recurrent Dirichlet Belief Network~(Recurrent-DBN) -- to study interpretable hidden structures from dynamic relational data. The proposed Recurrent-DBN has the following merits: (1) it infers interpretable and organised hierarchical latent structures for objects within and across time steps; (2) it enables recurrent long-term temporal dependence modelling, which outperforms the one-order Markov descriptions in most of the dynamic probabilistic frameworks. In addition, we develop a new inference strategy, which first upward-and-backward propagates latent counts and then downward-and-forward samples variables, to enable efficient Gibbs sampling for the Recurrent-DBN. We apply the Recurrent-DBN to dynamic relational data problems. The extensive experiment results on real-world data validate the advantages of the Recurrent-DBN over the state-of-the-art models in interpretable latent structure discovery and improved link prediction performance.

Qiang Lyu, Yixin Chen, Zhaorong Li et al.

A main focus of machine learning research has been improving the generalization accuracy and efficiency of prediction models. Many models such as SVM, random forest, and deep neural nets have been proposed and achieved great success. However, what emerges as missing in many applications is actionability, i.e., the ability to turn prediction results into actions. For example, in applications such as customer relationship management, clinical prediction, and advertisement, the users need not only accurate prediction, but also actionable instructions which can transfer an input to a desirable goal (e.g., higher profit repays, lower morbidity rates, higher ads hit rates). Existing effort in deriving such actionable knowledge is few and limited to simple action models which restricted to only change one attribute for each action. The dilemma is that in many real applications those action models are often more complex and harder to extract an optimal solution. In this paper, we propose a novel approach that achieves actionability by combining learning with planning, two core areas of AI. In particular, we propose a framework to extract actionable knowledge from random forest, one of the most widely used and best off-the-shelf classifiers. We formulate the actionability problem to a sub-optimal action planning (SOAP) problem, which is to find a plan to alter certain features of a given input so that the random forest would yield a desirable output, while minimizing the total costs of actions. Technically, the SOAP problem is formulated in the SAS+ planning formalism, and solved using a Max-SAT based approach. Our experimental results demonstrate the effectiveness and efficiency of the proposed approach on a personal credit dataset and other benchmarks. Our work represents a new application of automated planning on an emerging and challenging machine learning paradigm.