arXiv subjects

Shimin Di

Publications and source records attributed to Shimin Di.

50 records · Page 3Linked to original sources

arXiv2025

RemoteSAM: Towards Segment Anything for Earth Observation

We aim to develop a robust yet flexible visual foundation model for Earth observation. It should possess strong capabilities in recognizing and localizing diverse visual targets while providing compatibility with various input-output interfaces required across different task scenarios. Current systems cannot meet these requirements, as they typically utilize task-specific architecture trained on narrow data domains with limited semantic coverage. Our study addresses these limitations from two aspects: data and modeling. We first introduce an automatic data engine that enjoys significantly better scalability compared to previous human annotation or rule-based approaches. It has enabled us to create the largest dataset of its kind to date, comprising 270K image-text-mask triplets covering an unprecedented range of diverse semantic categories and attribute specifications. Based on this data foundation, we further propose a task unification paradigm that centers around referring expression segmentation. It effectively handles a wide range of vision-centric perception tasks, including classification, detection, segmentation, grounding, etc, using a single model without any task-specific heads. Combining these innovations on data and modeling, we present RemoteSAM, a foundation model that establishes new SoTA on several earth observation perception benchmarks, outperforming other foundation models such as Falcon, GeoChat, and LHRS-Bot with significantly higher efficiency. Models and data are publicly available at https://github.com/1e12Leon/RemoteSAM.

cs.CV↗

arXiv2025

Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPO

Previous study suggest that powerful Large Language Models (LLMs) trained with Reinforcement Learning with Verifiable Rewards (RLVR) only refines reasoning path without improving the reasoning capacity in math tasks while supervised-finetuning(SFT) with distillation can. We study this from the view of Scientific information extraction (SciIE) where LLMs and reasoning LLMs underperforms small Bert-based models. SciIE require both the reasoning and memorization. We argue that both SFT and RLVR can refine the reasoning path and improve reasoning capacity in a simple way based on SciIE. We propose two-stage training with 1. MimicSFT, using structured reasoning templates without needing high-quality chain-of-thought data, 2. R$^2$GRPO with relevance and rule-induced rewards. Experiments on scientific IE benchmarks show that both methods can improve the reasoning capacity. R$^2$GRPO with mimicSFT surpasses baseline LLMs and specialized supervised models in relation extraction. Our code is available at https://github.com/ranlislz/R2GRPO.

cs.CL↗

arXiv2025

A Pilot Empirical Study on When and How to Use Knowledge Graphs as Retrieval Augmented Generation

The integration of Knowledge Graphs (KGs) into the Retrieval Augmented Generation (RAG) framework has attracted significant interest, with early studies showing promise in mitigating hallucinations and improving model accuracy. However, a systematic understanding and comparative analysis of the rapidly emerging KG-RAG methods are still lacking. This paper seeks to lay the foundation for systematically answering the question of when and how to use KG-RAG by analyzing their performance in various application scenarios associated with different technical configurations. After outlining the mind map using KG-RAG framework and summarizing its popular pipeline, we conduct a pilot empirical study of KG-RAG works to reimplement and evaluate 6 KG-RAG methods across 9 datasets in diverse domains and scenarios, analyzing the impact of 9 KG-RAG configurations in combination with 17 LLMs, and combining Metacognition with KG-RAG as a pilot attempt. Our results underscore the critical role of appropriate application conditions and optimal configurations of KG-RAG components.

cs.AI↗

arXiv2025

DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation

Dynamic Retrieval-augmented Generation (RAG) has shown great success in mitigating hallucinations in large language models (LLMs) during generation. However, existing dynamic RAG methods face significant limitations in two key aspects: 1) Lack of an effective mechanism to control retrieval triggers, and 2) Lack of effective scrutiny of retrieval content. To address these limitations, we propose an innovative dynamic RAG method, DioR (Adaptive Cognitive Detection and Contextual Retrieval Optimization), which consists of two main components: adaptive cognitive detection and contextual retrieval optimization, specifically designed to determine when retrieval is needed and what to retrieve for LLMs is useful. Experimental results demonstrate that DioR achieves superior performance on all tasks, demonstrating the effectiveness of our work.

cs.CL↗

arXiv2025

Learning Towards Emergence: Paving the Way to Induce Emergence by Inhibiting Monosemantic Neurons on Pre-trained Models

Emergence, the phenomenon of a rapid performance increase once the model scale reaches a threshold, has achieved widespread attention recently. The literature has observed that monosemantic neurons in neural networks gradually diminish as the model scale increases. Subsequently, Learning From Emergence is proposed to actively inhibit monosemantic neurons in relatively small neural networks (e.g., BERT and Swin-Transformer) for promoting model performance with fine-tuning. However, to ultimately achieve emergence, it is demanding to support the monosemantic neuron inhibition in the pretraining phase of large-scale models. Thus, this work further pushes the boundary of this research direction to be Learning Towards Emergence (L2E) and enables the training and validating of the impact of inhibiting monosemantic neurons on larger pre-trained neural networks (e.g., Pythia-70M, 410M, and 2.8B). More specifically, to bridge the gap in current research, we first conduct experiments on models of various scales (up to 6.9B) to validate the monosemantic ideas. Then, we present a novel method L2E to address the inefficient monosemantic neuron retrieval and ineffective monosemantic neuron inhibition when existing methods are applied in the pretraining phase of large-scale models. It employs an adjustable thresholding technique for efficient neuron retrieval, incorporates a False Killing Rate metric to assess inhibition effects, and proposes a regularization-style inhibition approach, which addresses the limitations of previous approaches in both efficiency and effectiveness. Experimental results demonstrate the effectiveness of L2E's monosemantic neuron inhibition and its efficiency in implementation with large-scale models.

cs.ET↗

arXiv2025

A Selective Learning Method for Temporal Graph Continual Learning

Node classification is a key task in temporal graph learning (TGL). Real-life temporal graphs often introduce new node classes over time, but existing TGL methods assume a fixed set of classes. This assumption brings limitations, as updating models with full data is costly, while focusing only on new classes results in forgetting old ones. Graph continual learning (GCL) methods mitigate forgetting using old-class subsets but fail to account for their evolution. We define this novel problem as temporal graph continual learning (TGCL), which focuses on efficiently maintaining up-to-date knowledge of old classes. To tackle TGCL, we propose a selective learning framework that substitutes the old-class data with its subsets, Learning Towards the Future (LTF). We derive an upper bound on the error caused by such replacement and transform it into objectives for selecting and learning subsets that minimize classification error while preserving the distribution of the full old-class data. Experiments on three real-world datasets validate the effectiveness of LTF on TGCL.

cs.LG↗

arXiv2025

Cardinality Estimation on Hyper-relational Knowledge Graphs

Cardinality Estimation (CE) for query is to estimate the number of results without execution, which is an effective index in query optimization. Recently, CE for queries over knowlege graph (KGs) with triple facts has achieved great success. To more precisely represent facts, current researchers propose hyper-relational KGs (HKGs) to represent a triple fact with qualifiers providing additional context to the fact. However, existing CE methods, such as sampling and summary methods over KGs, perform unsatisfactorily on HKGs due to the complexity of qualifiers. Learning-based CE methods do not utilize qualifier information to learn query representation accurately, leading to poor performance. Also, there is only one limited CE benchmark for HKG query, which is not comprehensive and only covers limited patterns. The lack of querysets over HKG also becomes a bottleneck to comprehensively investigate CE problems on HKGs. In this work, we first construct diverse and unbiased hyper-relational querysets over three popular HKGs for investigating CE. Besides, we also propose a novel qualifier-aware graph neural network (GNN) model that effectively incorporates qualifier information and adaptively combines outputs from multiple GNN layers, to accurately predict the cardinality. Our experiments demonstrate that our model outperforms all state-of-the-art CE methods over three benchmarks on popular HKGs.

cs.LG↗

arXiv2025

UEMM-Air: Make Unmanned Aerial Vehicles Perform More Multi-modal Tasks

The development of multi-modal learning for Unmanned Aerial Vehicles (UAVs) typically relies on a large amount of pixel-aligned multi-modal image data. However, existing datasets face challenges such as limited modalities, high construction costs, and imprecise annotations. To this end, we propose a synthetic multi-modal UAV-based multi-task dataset, UEMM-Air. Specifically, we simulate various UAV flight scenarios and object types using the Unreal Engine (UE). Then we design the UAV's flight logic to automatically collect data from different scenarios, perspectives, and altitudes. Furthermore, we propose a novel heuristic automatic annotation algorithm to generate accurate object detection labels. Finally, we utilize labels to generate text descriptions of images to make our UEMM-Air support more cross-modality tasks. In total, our UEMM-Air consists of 120k pairs of images with 6 modalities and precise annotations. Moreover, we conduct numerous experiments and establish new benchmark results on our dataset. We also found that models pre-trained on UEMM-Air exhibit better performance on downstream tasks compared to other similar datasets. The dataset is publicly available (https://github.com/1e12Leon/UEMM-Air) to support the research of multi-modal tasks on UAVs.

cs.CV↗

arXiv2024

Class-aware and Augmentation-free Contrastive Learning from Label Proportion

Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label proportions per bag. This paradigm is essential for user modeling and personalization, where user privacy is paramount, offering insights into user preferences without revealing individual data. LLP faces a unique difficulty: the misalignment between bag-level supervision and the objective of instance-level prediction, primarily due to the inherent ambiguity in label proportion matching. Previous studies have demonstrated deep representation learning can generate auxiliary signals to promote the supervision level in the image domain. However, applying these techniques to tabular data presents significant challenges: 1) they rely heavily on label-invariant augmentation to establish multi-view, which is not feasible with the heterogeneous nature of tabular datasets, and 2) tabular datasets often lack sufficient semantics for perfect class distinction, making them prone to suboptimality caused by the inherent ambiguity of label proportion matching. To address these challenges, we propose an augmentation-free contrastive framework TabLLP-BDC that introduces class-aware supervision (explicitly aware of class differences) at the instance level. Our solution features a two-stage Bag Difference Contrastive (BDC) learning mechanism that establishes robust class-aware instance-level supervision by disassembling the nuance between bag label proportions, without relying on augmentations. Concurrently, our model presents a pioneering multi-task pretraining pipeline tailored for tabular-based LLP, capturing intrinsic tabular feature correlations in alignment with label proportion distribution. Extensive experiments demonstrate that TabLLP-BDC achieves state-of-the-art performance for LLP in the tabular domain.

cs.LG↗

arXiv2024

Learning from Emergence: A Study on Proactively Inhibiting the Monosemantic Neurons of Artificial Neural Networks

Recently, emergence has received widespread attention from the research community along with the success of large-scale models. Different from the literature, we hypothesize a key factor that promotes the performance during the increase of scale: the reduction of monosemantic neurons that can only form one-to-one correlations with specific features. Monosemantic neurons tend to be sparser and have negative impacts on the performance in large models. Inspired by this insight, we propose an intuitive idea to identify monosemantic neurons and inhibit them. However, achieving this goal is a non-trivial task as there is no unified quantitative evaluation metric and simply banning monosemantic neurons does not promote polysemanticity in neural networks. Therefore, we first propose a new metric to measure the monosemanticity of neurons with the guarantee of efficiency for online computation, then introduce a theoretically supported method to suppress monosemantic neurons and proactively promote the ratios of polysemantic neurons in training neural networks. We validate our conjecture that monosemanticity brings about performance change at different model scales on a variety of neural networks and benchmark datasets in different areas, including language, image, and physics simulation tasks. Further experiments validate our analysis and theory regarding the inhibition of monosemanticity.

cs.LG↗

arXiv2024

Search to Fine-tune Pre-trained Graph Neural Networks for Graph-level Tasks

Recently, graph neural networks (GNNs) have shown its unprecedented success in many graph-related tasks. However, GNNs face the label scarcity issue as other neural networks do. Thus, recent efforts try to pre-train GNNs on a large-scale unlabeled graph and adapt the knowledge from the unlabeled graph to the target downstream task. The adaptation is generally achieved by fine-tuning the pre-trained GNNs with a limited number of labeled data. Despite the importance of fine-tuning, current GNNs pre-training works often ignore designing a good fine-tuning strategy to better leverage transferred knowledge and improve the performance on downstream tasks. Only few works start to investigate a better fine-tuning strategy for pre-trained GNNs. But their designs either have strong assumptions or overlook the data-aware issue for various downstream datasets. Therefore, we aim to design a better fine-tuning strategy for pre-trained GNNs to improve the model performance in this paper. Given a pre-trained GNN, we propose to search to fine-tune pre-trained graph neural networks for graph-level tasks (S2PGNN), which adaptively design a suitable fine-tuning framework for the given labeled data on the downstream task. To ensure the improvement brought by searching fine-tuning strategy, we carefully summarize a proper search space of fine-tuning framework that is suitable for GNNs. The empirical studies show that S2PGNN can be implemented on the top of 10 famous pre-trained GNNs and consistently improve their performance. Besides, S2PGNN achieves better performance than existing fine-tuning strategies within and outside the GNN area. Our code is publicly available at \url{https://anonymous.4open.science/r/code_icde2024-A9CB/}.

cs.LG↗

arXiv2021

AutoGEL: An Automated Graph Neural Network with Explicit Link Information

Recently, Graph Neural Networks (GNNs) have gained popularity in a variety of real-world scenarios. Despite the great success, the architecture design of GNNs heavily relies on manual labor. Thus, automated graph neural network (AutoGNN) has attracted interest and attention from the research community, which makes significant performance improvements in recent years. However, existing AutoGNN works mainly adopt an implicit way to model and leverage the link information in the graphs, which is not well regularized to the link prediction task on graphs, and limits the performance of AutoGNN for other graph tasks. In this paper, we present a novel AutoGNN work that explicitly models the link information, abbreviated to AutoGEL. In such a way, AutoGEL can handle the link prediction task and improve the performance of AutoGNNs on the node classification and graph classification task. Specifically, AutoGEL proposes a novel search space containing various design dimensions at both intra-layer and inter-layer designs and adopts a more robust differentiable search algorithm to further improve efficiency and effectiveness. Experimental results on benchmark data sets demonstrate the superiority of AutoGEL on several tasks.

cs.LG↗

arXiv2021

Efficient Relation-aware Scoring Function Search for Knowledge Graph Embedding

The scoring function, which measures the plausibility of triplets in knowledge graphs (KGs), is the key to ensure the excellent performance of KG embedding, and its design is also an important problem in the literature. Automated machine learning (AutoML) techniques have recently been introduced into KG to design task-aware scoring functions, which achieve state-of-the-art performance in KG embedding. However, the effectiveness of searched scoring functions is still not as good as desired. In this paper, observing that existing scoring functions can exhibit distinct performance on different semantic patterns, we are motivated to explore such semantics by searching relation-aware scoring functions. But the relation-aware search requires a much larger search space than the previous one. Hence, we propose to encode the space as a supernet and propose an efficient alternative minimization algorithm to search through the supernet in a one-shot manner. Finally, experimental results on benchmark datasets demonstrate that the proposed method can efficiently search relation-aware scoring functions, and achieve better embedding performance than state-of-the-art methods.

cs.LG↗

arXiv2021

Searching to Sparsify Tensor Decomposition for N-ary Relational Data

Tensor, an extension of the vector and matrix to the multi-dimensional case, is a natural way to describe the N-ary relational data. Recently, tensor decomposition methods have been introduced into N-ary relational data and become state-of-the-art on embedding learning. However, the performance of existing tensor decomposition methods is not as good as desired. First, they suffer from the data-sparsity issue since they can only learn from the N-ary relational data with a specific arity, i.e., parts of common N-ary relational data. Besides, they are neither effective nor efficient enough to be trained due to the over-parameterization problem. In this paper, we propose a novel method, i.e., S2S, for effectively and efficiently learning from the N-ary relational data. Specifically, we propose a new tensor decomposition framework, which allows embedding sharing to learn from facts with mixed arity. Since the core tensors may still suffer from the over-parameterization, we propose to reduce parameters by sparsifying the core tensors while retaining their expressive power using neural architecture search (NAS) techniques, which can search for data-dependent architectures. As a result, the proposed S2S not only guarantees to be expressive but also efficiently learns from mixed arity. Finally, empirical results have demonstrated that S2S is efficient to train and achieves state-of-the-art performance.

cs.LG↗