Large Language Models (LLMs) have demonstrated a remarkable understanding of language nuances through instruction tuning, enabling them to effectively tackle various natural language processing tasks.Recent research has focused on the quality of instruction data rather than the quantity of instructions.However, existing high-quality instruction selection methods rely on external models or rules, overlooking the intrinsic association between pretrained model and instruction data, making it difficult to select data that align with the preferences of pre-trained model.To address this challenge, we propose a strategy that utilizes noise injection to identify the quality of instruction data, without relying on external model.We also implement the strategy of combining inter-class diversity and intra-class diversity to improve model performance.The experimental results demonstrate that our method significantly outperforms the model trained on the entire dataset and established baselines.Our study provides a new perspective on noise injection in the field of instruction tuning, and also illustrates that the pre-trained model itself should be considered in defining high-quality.Additionally, we publish our selected highquality instruction data at https://github. com/HUSTNLP-codes/Alpaca-selectd.

Temporal evolution attribute graph prediction, a key task in graph machine learning, aims to forecast the dynamic evolution of node attributes over time.While recent advances in Large Language Models (LLMs) have enabled their use in enhancing node representations for integration with Graph Neural Networks (GNNs), their potential to directly perform GNN-like aggregation and interaction remains underexplored.Furthermore, traditional approaches to initializing attribute embeddings often disregard structural semantics, limiting the provision of rich prior knowledge to GNNs.Current methods also primarily focus on 1-hop neighborhood aggregation, lacking the capability to capture complex structural interactions.To address these limitations, we propose a novel prediction framework that integrates structural information into attribute embeddings through the introduction of an attribute embedding loss.We design specialized prompts to enable LLMs to perform GNN-like aggregation and incorporate a relation-aware Graph Convolutional Network to effectively capture long-range and complex structural dependencies.Extensive experiments on multiple real-world datasets validate the effectiveness of our approach, demonstrating significant improvements in predictive performance over existing methods.

Multimodal knowledge graph (MKG) reasoning has attracted significant attention since impressive performance has been achieved by adding multimodal auxiliary information (i.e., texts and images) to the entities of traditional KGs. However, existing studies heavily rely on path-based methods for learning structural modality, failing to capture the complex structural interactions among multimodal entities beyond the reasoning path. In addition, existing studies have largely ignored the dynamic impact of different multimodal features on different decision facts for reasoning, which utilize asymmetric coattention to independently learn the static interplay between different modalities without dynamically joining the reasoning process. We propose a novel Dynamic Structure-aware representation learning method, namely DySarl, to overcome this problem and significantly improve the MKG reasoning performance. Specifically, we devise a dual-space multihop structural learning module in DySarl, aggregating the multihop structural features of multimodal entities via a novel message-passing mechanism. It integrates the message paradigms in Euclidean and hyperbolic spaces, effectively preserving the neighborhood information beyond the limited multimodal query paths. Furthermore, DySarl has an interactive symmetric attention module to explicitly learn the dynamic impacts of unimodal attention senders and multimodal attention targets on decision facts through a newly designed symmetric attention component and fact-specific gated attention unit, equipping DySarl with the dynamic associations between the multimodal feature learning and later reasoning. Extensive experiments show that DySarl achieves significantly improved reasoning performance on two public MKG datasets compared with that of the state-of-the-art baselines. Source codes are available at https://github.com/HUSTNLP-codes/DySarl.

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations; therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands" problem of relation modeling. On the other hand, ignoring the association constraints between relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). About the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://github.com/CGCL-codes/RETIA.

Temporal knowledge graph (TKG) forecasting is widely used in various fields due to its ability to infer future events based on historical information. Modeling the internal structures and chronological dependencies of historical subgraph sequences has been proven effective. Nevertheless, on the one hand, the TKG forecasting process generally suffers from a lack of sufficient sample data due to historical resource limitations; thus, most works focus on continuously mining the patterns of historical sequences while ignoring the semantically-rich background information provided by external knowledge, especially when historical query-related information is scarce. On the other hand, when merely serializing the given subgraph sequence to mimic its temporal evolution process, only the chronological dependencies between the subgraphs can be considered, thus ignoring the evolution of time information. Hence, a method that integrates internal and external knowledge to enhance the representations of entities is urgently needed. To this end, we propose a novel TKG forecasting method, namely, the internal and external evolution-enhanced framework (IE-Evo). For the former issue, we design an external evolution encoder and use a pre-trained language model (PLM) to provide powerful external knowledge semantics for TKG forecasting. To address the latter concern, we propose an internal evolution encoder that explicitly embeds the time information while modeling the aggregation and evolution processes of the observed sequential structural information. IE-Evo has been evaluated on four public benchmark datasets, showcasing its significant improvements across multiple evaluation metrics.

Predicting future events in dynamic knowledge graphs has attracted significant attention. Existing work models the historical information in a holistic way, which achieves satisfactory performance. However, in real-world scenarios, the influence of historical information on future events is changing over time. Therefore, it is difficult to distinguish the historical information of different roles by invariably embedding historical entities with simple vector stacking. Furthermore, it is laborious to explicitly learn a distributed representation of each historical repetitive fact at different timestamps. This poses a challenge to the widely adopted codec-based architectures. In this paper, we propose a novel model for predicting future events, namely Distributed Attention Network (DA-Net). Rather than obtaining the fixed representations of historical events, DA-Net attempts to learn the distributed attention of future events on repetitive facts at different historical timestamps inspired by human cognitive theory. In human cognitive theory, when humans make a decision, similar historical events are replayed during memory recall. Based on memory, the original intention is adjusted according to their recent knowledge developments, making the action more reasonable to the context. Experiments on four benchmark datasets demonstrate a substantial improvement of DA-Net on multiple evaluation metrics.

Temporal knowledge graph (TKG) reasoning has attracted significant attention. Recent approaches for modeling historical information have led to great advances. However, the problems of time variability and unseen entities have become two major obstacles preventing further development. The time variability problem means that different historical timestamps play different roles in the inference process. Furthermore, in the context of time variability, the unseen entity problem means that a query cannot obtain a predicted entity that is unseen in the scale-varying history rather than in a fixed set, thus turning from static to dynamic. In this paper, we propose a novel method named DHU-NET for addressing the time variability challenge and the dynamic unseen entity challenge derived from it. With regard to the former concern, we propose a time-distributed representation learning method based on a graph convolutional network(GCN) and a self-attention mechanism, which learns the distributed representations of facts at different historical timestamps and comprehensively pays different levels of attention to the different timestamps. With regard to the latter issue, we extract the unseen entities from a global static KG based on a copy mechanism and bring them into consideration during the final prediction step. Experiments on six benchmark datasets demonstrate the substantial improvements achieved by DHUNET in terms of multiple evaluation metrics. Our released codes are available at https://github.com/CGCL-codes/DHUNET.