Large language models (LLMs) have recently empowered multi-agent systems (MAS) to achieve remarkable advances in collaborative reasoning and complex task automation. The effectiveness of these systems fundamentally depends on the design of adaptive communication graphs—the underlying workflows that coordinate agent interactions. However, in real-world scenarios, strict privacy constraints often silo data across organizations, and client distributions are highly non-IID, posing major challenges for synthesizing such workflows. In this work, we are the first to systematically study distributed multi-agent workflow synthesis under these privacy and heterogeneity constraints, and we introduce the Difficulty-Based Skew (DBS) benchmark to emulate such challenging environments. Drawing inspiration from federated graph learning (FGL)—which has primarily focused on classification over static graphs—we identify a critical gap: existing FGL methods do not address the generative design of communication topologies. We reveal two fundamental obstacles to generative workflow synthesis in this setting: (i) workflow specialization conflict, where agents optimized for different task distributions generate incompatible communication patterns that resist meaningful aggregation, and (ii) structural communication shift, where locally optimal agent interaction graphs fail to compose into globally coherent multi-agent workflows. To address these challenges, we propose DAWN, a federated framework that integrates two key innovations: Parametric Resonance, which robustly aggregates heterogeneous local updates via layer-wise SVD-based denoising and alignment, and Structural Gravity, which regularizes local workflow generation by penalizing the Fusion Gromov-Wasserstein distance to a set of prototype communication graphs, ensuring global structural coherence without stifling local adaptation. Experiments on the DBS benchmark show that DAWN surpasses baselines in global task success and reduces inter-client graph divergence, laying a solid foundation for privacy-preserving, adaptive MAS workflow design in heterogeneous settings.

Multimodal large language models (MLLMs) frequently hallucinate by over-committing to spurious visual cues. Prior remedies–Visual and Instruction Contrastive Decoding (VCD, ICD)–mitigate this issue, yet the mechanism remains opaque. We first empirically show that their improvements systematically coincide with redistributions of cross-modal attention. Building on this insight, we propose Attention-Steerable Contrastive Decoding (ASCD), which directly steers the attention scores during decoding. ASCD combines (i) positive steering, which amplifies automatically mined text-centric heads–stable within a model and robust across domains–with (ii) negative steering, which dampens on-the-fly identified critical visual tokens. The method incurs negligible runtime/memory overhead and requires no additional training. Across five MLLM backbones and three decoding schemes, ASCD reduces hallucination on POPE, CHAIR, and MMHal-Bench by up to 38.2% while improving accuracy on standard VQA benchmarks, including MMMU, MM-VET, ScienceQA, TextVQA, and GQA. These results position attention steering as a simple, model-agnostic, and principled route to safer, more faithful multimodal generation.

We present OpenDriveVLA, a Vision-Language Action (VLA) model designed for end-to-end autonomous driving, built upon open-source large language models. OpenDriveVLA generates spatially-grounded driving actions by leveraging multimodal inputs, including both 2D and 3D instance-aware visual representations, ego vehicle states, and language commands. To bridge the modality gap between driving visual representations and language embeddings, we introduce a hierarchical vision-language alignment process, projecting both 2D and 3D structured visual tokens into a unified semantic space. Furthermore, we incorporate structured agent–environment–ego interaction modeling into the autoregressive decoding process, enabling the model to capture fine-grained spatial dependencies and behavior-aware dynamics critical for reliable trajectory planning. Extensive experiments on the nuScenes dataset demonstrate that OpenDriveVLA achieves state-of-the-art results across open-loop trajectory planning and driving-related question-answering tasks. Qualitative analyses further illustrate its superior capability to follow high-level driving commands and robustly generate trajectories under challenging scenarios, highlighting its potential for next-generation end-to-end autonomous driving.

Zihao Cheng, Zeming Liu, Yingyu Shan, Xinyi Wang, Xiangrong Zhu, Yunpu Ma, Hongru Wang, Yuhang Guo, Wei Lin, Yunhong Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Jinhe Bi, Kristian Kersting, Jeff Z. Pan, Hinrich Schuetze, Volker Tresp, Yunpu Ma. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

LLM-based autonomous agents often fail to execute complex web tasks that require dynamic interaction, largely due to the inherent uncertainty and complexity of these environments. Existing LLM-based web agents typically rely on rigid, expert-designed policies specific to certain states and actions, lacking the flexibility and generalizability needed to adapt to unseen tasks. In contrast, humans excel by exploring unknowns, continuously adapting strategies based on new observations, and resolving ambiguities through exploration. To emulate human-like adaptability, web agents need strategic exploration and complex decision-making. Monte Carlo Tree Search (MCTS) is well-suited for this, but classical MCTS struggles with vast action spaces, unpredictable state transitions, and incomplete information in web tasks. In light of this, we develop WebPilot, a multi-agent system with a dual optimization strategy that improves MCTS to better handle complex web environments. Specifically, the Global Optimization phase involves generating a high-level plan by breaking down tasks into manageable subtasks, continuously refining this plan through reflective analysis of new observations and previous subtask attempts, thereby focusing the search process and mitigating challenges posed by vast action spaces in classical MCTS. Subsequently, the Local Optimization phase executes each subtask using a tailored MCTS designed for complex environments, effectively addressing uncertainties and managing incomplete information by iteratively refining decisions based on new observations. Experimental results on WebArena and MiniWoB++ demonstrate the effectiveness of WebPilot. Notably, on WebArena, WebPilot achieves SOTA performance with GPT-4, achieving a 93% relative increase in success rate over the concurrent tree search-based method. WebPilot advances autonomous agents, enabling more reliable decision-making in practical environments.

Jinhe Bi, Yujun Wang, Haokun Chen, Xun Xiao, Artur Hecker, Volker Tresp, Yunpu Ma. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity.To evaluate retrieval beyond these shallow signals, recent benchmarks introduce reasoning-heavy queries; however, they primarily shift the burden to query-side processing techniques -like prompting or multi-hop retrieval -that can help resolve complexity.In contrast, we present IMPLIRET, a benchmark that shifts the reasoning challenge to documentside processing: The queries are simple, but relevance depends on facts stated implicitly in documents through temporal (e.g., resolving "two days ago"), arithmetic, and world knowledge relationships.We evaluate a range of sparse and dense retrievers, all of which struggle in this setting: the best nDCG@10 is only 14.91%.We also test whether long-context models can overcome this limitation.But even with a short context of only thirty documents, including the positive document, GPT-o4-mini scores only 55.54%, showing that document-side reasoning remains a challenge.Our codes are available at github.com/ZeinabTaghavi/IMPLIRET.

Recent advances in Video Large Language Models (VLLMs) have significantly enhanced their ability to understand video content. Nonetheless, processing long videos remains challenging due to high computational demands and the redundancy present in the visual data. In this work, we propose \textbf{METok}, a training-free, \textbf{M}ulti-stage \textbf{E}vent-based \textbf{Tok}en compression framework designed to accelerate VLLMs’ inference while preserving accuracy. METok progressively eliminates redundant visual tokens across three critical stages: (1) event-aware compression during vision encoding, (2) hierarchical token pruning in the prefilling stage based on semantic alignment and event importance, and (3) a decoding-stage KV Cache optimization that further reduces memory consumption. Our experiments on diverse video benchmarks demonstrate that METok achieves an optimal trade-off between efficiency and accuracy by dynamically selecting informative visual tokens. For instance, equipping LongVA-7B with METok realizes an 80.6% FLOPs reduction and 93.5% KV Cache memory savings, all while maintaining comparable or even superior accuracy.

Reasoning language models (RLMs) excel at complex tasks by leveraging a chain-of-thought process to generate structured intermediate steps.However, language mixing, i.e., reasoning steps containing tokens from languages other than the prompt, has been observed in their outputs and shown to affect performance, though its impact remains debated.We present the first systematic study of language mixing in RLMs, examining its patterns, impact, and internal causes across 15 languages, 7 task difficulty levels, and 18 subject areas, and show how all three factors influence language mixing.Moreover, we demonstrate that the choice of reasoning language significantly affects performance: forcing models to reason in Latin or Han scripts via constrained decoding notably improves accuracy.Finally, we show that the script composition of reasoning traces closely aligns with that of the model's internal representations, indicating that language mixing reflects latent processing preferences in RLMs.Our findings provide actionable insights for optimizing multilingual reasoning and open new directions for controlling reasoning languages to build more interpretable and adaptable RLMs. 1 4 This overthinking behavior is also observed in prior work such as Cuadron et al. (2025).

The rapid progress of Large Language Models has advanced agentic systems in decisionmaking, coordination, and task execution.Yet, existing agentic system generation frameworks lack full autonomy, missing from-scratch agent generation, self-optimizing agent functionality, and collaboration, limiting adaptability and scalability.We propose SwarmAgentic, the first framework that fully automates agentic system generation, optimization, and collaboration, constructing agents from scratch and jointly refining functionality and coordination via language-driven exploration.To enable efficient search over system-level structures, SwarmAgentic maintains a population of candidate systems and evolves them via feedbackguided updates, drawing inspiration from Particle Swarm Optimization (PSO).We evaluate our method on six real-world, open-ended, and exploratory tasks involving high-level planning, system-level coordination, and creative reasoning.Given only a task description and an objective function, SwarmAgentic outperforms all baselines, achieving a +261.8%relative improvement over ADAS on the Trav-elPlanner benchmark, highlighting the effectiveness of full automation in structurally unconstrained tasks.This framework marks a significant step toward scalable and autonomous agentic system design, bridging swarm intelligence with fully automated system multi-agent generation.Our code is publicly released at github.com/SwarmAgentic.

The Job shop scheduling problem (JSSP) plays a pivotal role in industrial applications, such as signal processing (SP) and steel manufacturing, involving sequencing machines and jobs to maximize scheduling efficiency. Before, JSSP was solved using manually defined circuits by variational quantum algorithm (VQA). Finding a good circuit architecture is task-specific and time-consuming. Differentiable quantum architecture search (DQAS) is a gradient-based framework that can automatically design circuits. However, DQAS is only tested on quantum approximate optimization algorithm (QAOA) and error mitigation tasks. Whether DQAS applies to JSSP based on a more flexible algorithm, such as variational quantum eigensolver (VQE), is still open for optimization problems. In this work, we redefine the operation pool and extend DQAS to a framework JSSP-DQAS by evaluating circuits to generate circuits for JSSP automatically. The experiments conclude that JSSP-DQAS can automatically find noise-resilient circuit architectures that perform much better than manually designed circuits. It helps to improve the efficiency of solving JSSP.

Zifeng Ding, Heling Cai, Jingpei Wu, Yunpu Ma, Ruotong Liao, Bo Xiong, Volker Tresp. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Explanations play an essential role in helping users evaluate results from recommender systems. Various natural language generation methods have been proposed to generate explanations for the recommendation. However, they usually suffer from two problems. First, since user-provided review text contains noisy data, the generated explanations may be irrelevant to the recommended items. Second, as lacking some supervision signals, most of the generated sentences are similar, which cannot meet the diversity and personalized needs of users. To tackle these problems, we propose a multimodal contrastive transformer (MMCT) model for an explainable recommendation, which incorporates multimodal information into the learning process, including sentiment features, item features, item images, and refined user reviews. Meanwhile, we propose a dynamic fusion mechanism during the decoding stage, which generates supervision signals to guide the explanation generation. Additionally, we develop a contrastive objective to generate diverse explainable texts. Comprehensive experiments on two real-world datasets show that the proposed model outperforms comparable explainable recommendation baselines in terms of explanation performance and recommendation performance. Efficiency analysis and robustness analysis verify the advantages of the proposed model. While ablation analysis establishes the relative contributions of the respective components and various modalities, the case study shows the working of our model from an intuitive sense.

Few-shot relational learning for static knowledge graphs (KGs) has drawn greater interest in recent years, while few-shot learning for temporal knowledge graphs (TKGs) has hardly been studied. Compared to KGs, TKGs contain rich temporal information, thus requiring temporal reasoning techniques for modeling. This poses a greater challenge in learning few-shot relations in the temporal context. In this paper, we follow the previous work that focuses on few-shot relational learning on static KGs and extend two fundamental TKG reasoning tasks, i.e., interpolated and extrapolated link prediction, to the one-shot setting. We propose four new large-scale benchmark datasets and develop a TKG reasoning model for learning one-shot relations in TKGs. Experimental results show that our model can achieve superior performance on all datasets in both TKG link prediction tasks.

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity with respect to the sequence length, the self-attention mechanism only processes information at the same scale, i.e., all attention heads are in the same resolution, resulting in the limited power of the Transformer. To remedy this, we propose a novel and efficient structure named Adaptive Multi-Resolution Attention (AdaMRA for short), which scales linearly to sequence length in terms of time and space. Specifically, we leverage a multi-resolution multi-head attention mechanism, enabling attention heads to capture long-range contextual information in a coarse-to-fine fashion. Moreover, to capture the potential relations between query representation and clues of different attention granularities, we leave the decision of which resolution of attention to use to query, which further improves the model's capacity compared to the vanilla Transformer. In an effort to reduce complexity, we adopt kernel attention without degrading the performance. Extensive experiments demonstrate the effectiveness and efficiency of our model by achieving state-of-the-art speed-memory-accuracy trade-off. To facilitate AdaMRA utilization by the scientific community, the implementation will be made publicly available.

Various adaptation methods, such as LoRA, prompts, and adapters, have been proposed to enhance the performance of pre-trained vision-language models in specific domains. As test samples in real-world applications usually differ from adaptation data, the robustness of these adaptation methods against distribution shifts are essential. In this study, we assess the robustness of 11 widely-used adaptation methods across 4 vision-language datasets under multimodal corruptions. Concretely, we introduce 7 benchmark datasets, including 96 visual and 87 textual corruptions, to investigate the robustness of different adaptation methods, the impact of available adaptation examples, and the influence of trainable parameter size during adaptation. Our analysis reveals that: 1) Adaptation methods are more sensitive to text corruptions than visual corruptions. 2) Full fine-tuning does not consistently provide the highest robustness; instead, adapters can achieve better robustness with comparable clean performance. 3) Contrary to expectations, our findings indicate that increasing the number of adaptation data and parameters does not guarantee enhanced robustness; instead, it results in even lower robustness. We hope this study could benefit future research in the development of robust multimodal adaptation methods. The benchmark, code, and dataset used in this study can be accessed at https://adarobustness.github.io.

Abstract Financial portfolio managers typically face multi-period optimization tasks such as short-selling or investing at least a particular portion of the portfolio in a specific industry sector. A common approach to tackle these problems is to use constrained Markov decision process (CMDP) methods, which may suffer from sample inefficiency, hyperparameter tuning, and lack of guarantees for constraint violations. In this paper, we propose Action Space Decomposition Based Optimization (ADBO) for optimizing a more straightforward surrogate task that allows actions to be mapped back to the original task. We examine our method on two real-world data portfolio construction tasks. The results show that our new approach consistently outperforms state-of-the-art benchmark approaches for general CMDPs.

We present a unified computational theory of an agent's perception and memory. In our model, both perception and memory are realized by different operational modes of the oscillating interactions between a symbolic index layer and a subsymbolic representation layer. The two layers form a bilayer tensor network (BTN). The index layer encodes indices for concepts, predicates, and episodic instances. The representation layer broadcasts information and reflects the cognitive brain state; it is our model of what authors have called the "mental canvas" or the "global workspace." As a bridge between perceptual input and the index layer, the representation layer enables the grounding of indices by their subsymbolic embeddings, which are implemented as connection weights linking both layers. The propagation of activation to earlier perceptual processing layers in the brain can lead to embodiments of indices. Perception and memories first create subsymbolic representations, which are subsequently decoded semantically to produce sequences of activated indices that form symbolic triple statements. The brain is a sampling engine: only activated indices are communicated to the remaining parts of the brain. Triple statements are dynamically embedded in the representation layer and embodied in earlier processing layers: the brain speaks to itself. Although memory appears to be about the past, its main purpose is to support the agent in the present and the future. Recent episodic memory provides the agent with a sense of the here and now. Remote episodic memory retrieves relevant past experiences to provide information about possible future scenarios. This aids the agent in decision making. "Future" episodic memory, based on expected future events, guides planning and action. Semantic memory retrieves specific information, which is not delivered by current perception, and defines priors for future observations. We argue that it is important for the agent to encode individual entities, not just classes and attributes. Perception is learning: episodic memories are constantly being formed, and we demonstrate that a form of self-supervised learning can acquire new concepts and refine existing ones. We test our model on a standard benchmark data set, which we expanded to contain richer representations for attributes, classes, and individuals. Our key hypothesis is that obtaining a better understanding of perception and memory is a crucial prerequisite to comprehending human-level intelligence.

Conventional static knowledge graphs model entities in relational data as nodes, connected by edges of specific relation types. However, information and knowledge evolve continuously, and temporal dynamics emerge, which are expected to influence future situations. In temporal knowledge graphs, time information is integrated into the graph by equipping each edge with a timestamp or a time range. Embedding-based methods have been introduced for link prediction on temporal knowledge graphs, but they mostly lack explainability and comprehensible reasoning chains. Particularly, they are usually not designed to deal with link forecasting -- event prediction involving future timestamps. We address the task of link forecasting on temporal knowledge graphs and introduce TLogic, an explainable framework that is based on temporal logical rules extracted via temporal random walks. We compare TLogic with state-of-the-art baselines on three benchmark datasets and show better overall performance while our method also provides explanations that preserve time consistency. Furthermore, in contrast to most state-of-the-art embedding-based methods, TLogic works well in the inductive setting where already learned rules are transferred to related datasets with a common vocabulary.

Active learning has the power to significantly reduce the amount of labeled data needed to build strong classifiers. Existing active pseudo-labeling methods show high potential in integrating pseudo-labels within the active learning loop but heavily depend on the prediction accuracy of the model. In this work, we propose VERIPS, an algorithm that significantly outperforms existing pseudo-labeling techniques for active learning. At its core, VERIPS uses a pseudo-label verification mechanism that consists of a second network only trained on data approved by the oracle and helps to discard questionable pseudo-labels. In particular, the verifier model eliminates all pseudo-labels for which it disagrees with the actual task model. VERIPS overcomes the problems of poorly performing initial models, e.g., due to imbalanced or too small initial pools, where previous methods select too many incorrect pseudo-labels and recovering takes long or is not possible. Moreover, VERIPS is particularly insensitive to parameter choices that existing approaches suffer from. Our code is available at https://github.com/lmu-dbs/VERIPS.

Personalized recommendation plays a central role in various online applications. To provide quality recommendation service, it is of crucial importance to consider multi-modal information associated with users and items, e.g., review text, description text, and images. However, many existing approaches do not fully explore and fuse multiple modalities. To address this problem, we propose a multi-modal contrastive pre-training model for recommendation. We first construct a homogeneous item graph and a user graph based on the relationship of co-interaction. For users, we propose intra-modal aggregation and inter-modal aggregation to fuse review texts and the structural information of the user graph. For items, we consider three modalities: description text, images, and item graph. Moreover, the description text and image complement each other for the same item. One of them can be used as promising supervision for the other. Therefore, to capture this signal and better exploit the potential correlation of intra-modalities, we propose a self-supervised contrastive inter-modal alignment task to make the textual and visual modalities as similar as possible. Then, we apply inter-modal aggregation to obtain the multi-modal representation of items. Next, we employ a binary cross-entropy loss function to capture the potential correlation between users and items. Finally, we fine-tune the pre-trained multi-modal representations using an existing recommendation model. We have performed extensive experiments on three real-world datasets. Experimental results verify the rationality and effectiveness of the proposed method.

Yiran Xing, Zai Shi, Zhao Meng, Gerhard Lakemeyer, Yunpu Ma, Roger Wattenhofer. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Estimating individual treatment effects from data of randomized experiments is a critical task in causal inference. The Stable Unit Treatment Value Assumption (SUTVA) is usually made in causal inference. However, interference can introduce bias when the assigned treatment on one unit affects the potential outcomes of the neighboring units. This interference phenomenon is known as spillover effect in economics or peer effect in social science. Usually, in randomized experiments or observational studies with interconnected units, one can only observe treatment responses under interference. Hence, the issue of how to estimate the superimposed causal effect and recover the individual treatment effect in the presence of interference becomes a challenging task in causal inference. In this work, we study causal effect estimation under general network interference using Graph Neural Networks, which are powerful tools for capturing node and link dependencies in graphs. After deriving causal effect estimators, we further study intervention policy improvement on the graph under capacity constraint. We give policy regret bounds under network interference and treatment capacity constraint. Furthermore, a heuristic graph structure-dependent error bound for Graph Neural Network-based causal estimators is provided.

There has been an increasing interest in inferring future links on temporal knowledge graphs (KG).While links on temporal KGs vary continuously over time, the existing approaches model the temporal KGs in discrete state spaces.To this end, we propose a novel continuum model by extending the idea of neural ordinary differential equations (ODEs) to multi-relational graph convolutional networks.The proposed model preserves the continuous nature of dynamic multi-relational graph data and encodes both temporal and structural information into continuous-time dynamic embeddings.In addition, a novel graph transition layer is applied to capture the transitions on the dynamic graph, i.e., edge formation and dissolution.We perform extensive experiments on five benchmark datasets for temporal KG reasoning, showing our model's superior performance on the future link forecasting task.

Various temporal knowledge graph (KG) completion models have been proposed in the recent literature.The models usually contain two parts, a temporal embedding layer and a score function derived from existing static KG modeling approaches.Since the approaches differ along several dimensions, including different score functions and training strategies, the individual contributions of different temporal embedding techniques to model performance are not always clear.In this work, we systematically study six temporal embedding approaches and empirically quantify their performance across a wide range of configurations with about 4000 experiments and 19000 GPU hours.We classify the temporal embeddings into two classes: (1) timestamp embeddings and (2) time-dependent entity embeddings.Despite the common belief that the latter is more expressive, an extensive experimental study shows that timestamp embeddings can achieve on-par or even better performance with significantly fewer parameters.Moreover, we find that when trained appropriately, the relative performance differences between various temporal embeddings often shrink and sometimes even reverse when compared to prior results.For example, TTransE (Leblay and Chekol, 2018), one of the first temporal KG models, can outperform more recent architectures on ICEWS datasets.To foster further research, we provide the first unified open-source framework for temporal KG completion models with full composability, where temporal embeddings, score functions, loss functions, regularizers, and the explicit modeling of reciprocal relations can be combined arbitrarily.

Temporal knowledge graph (TKG) reasoning is a crucial task that has gained increasing research interest in recent years.Most existing methods focus on reasoning at past timestamps to complete the missing facts, and there are only a few works of reasoning on known TKGs to forecast future facts.Compared with the completion task, the forecasting task is more difficult and faces two main challenges: (1) how to effectively model the time information to handle future timestamps?(2) how to make inductive inference to handle previously unseen entities that emerge over time?To address these challenges, we propose the first reinforcement learning method for forecasting.Specifically, the agent travels on historical knowledge graph snapshots to search for the answer.Our method defines a relative time encoding function to capture the timespan information, and we design a novel time-shaped reward based on Dirichlet distribution to guide the model learning.Furthermore, we propose a novel representation method for unseen entities to improve the inductive inference ability of the model.We evaluate our method for this link prediction task at future timestamps.Extensive experiments on four benchmark datasets demonstrate substantial performance improvement meanwhile with higher explainability, less calculation, and fewer parameters when compared with existing stateof-the-art methods.

Semantic knowledge graphs are large-scale triple-oriented databases for knowledge representation and reasoning. Implicit knowledge can be inferred by modeling the tensor representations generated from knowledge graphs. However, as the sizes of knowledge graphs continue to grow, classical modeling becomes increasingly computationally resource intensive. This article investigates how to capitalize on quantum resources to accelerate the modeling of knowledge graphs. In particular, we propose the first quantum machine learning algorithm for inference on tensorized data, i.e., on knowledge graphs. Since most tensor problems are NP-hard [18], it is challenging to devise quantum algorithms to support the inference task. We simplify the modeling task by making the plausible assumption that the tensor representation of a knowledge graph can be approximated by its low-rank tensor singular value decomposition, which is verified by our experiments. The proposed sampling-based quantum algorithm achieves speedup with a polylogarithmic runtime in the dimension of knowledge graph tensor.

We propose a novel method for automatic reasoning on knowledge graphs based on debate dynamics. The main idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments – paths in the knowledge graph – with the goal to promote the fact being true (thesis) or the fact being false (antithesis), respectively. Based on these arguments, a binary classifier, called the judge, decides whether the fact is true or false. The two agents can be considered as sparse, adversarial feature generators that present interpretable evidence for either the thesis or the antithesis. In contrast to other black-box methods, the arguments allow users to get an understanding of the decision of the judge. Since the focus of this work is to create an explainable method that maintains a competitive predictive accuracy, we benchmark our method on the triple classification and link prediction task. Thereby, we find that our method outperforms several baselines on the benchmark datasets FB15k-237, WN18RR, and Hetionet. We also conduct a survey and find that the extracted arguments are informative for users.

Story generation, which aims to generate a long and coherent story automatically based on the title or an input sentence, is an important research area in the field of natural language generation. There is relatively little work on story generation with appointed emotions. Most existing works focus on using only one specific emotion to control the generation of a whole story and ignore the emotional changes in the characters in the course of the story. In our work, we aim to design an emotional line for each character that considers multiple emotions common in psychological theories, with the goal of generating stories with richer emotional changes in the characters. To the best of our knowledge, this work is first to focuses on characters' emotional lines in story generation. We present a novel model-based attention mechanism that we call SoCP (Storytelling of multi-Character Psychology). We show that the proposed model can generate stories considering the changes in the psychological state of different characters. To take into account the particularity of the model, in addition to commonly used evaluation indicators(BLEU, ROUGE, etc.), we introduce the accuracy rate of psychological state control as a novel evaluation metric. The new indicator reflects the effect of the model on the psychological state control of story characters. Experiments show that with SoCP, the generated stories follow the psychological state for each character according to both automatic and human evaluations.

There has recently been increasing interest in learning representations of temporal knowledge graphs (KGs), which record the dynamic relationships between entities over time.Temporal KGs often exhibit multiple simultaneous non-Euclidean structures, such as hierarchical and cyclic structures.However, existing embedding approaches for temporal KGs typically learn entity representations and their dynamic evolution in the Euclidean space, which might not capture such intrinsic structures very well.To this end, we propose Dy-ERNIE, a non-Euclidean embedding approach that learns evolving entity representations in a product of Riemannian manifolds, where the composed spaces are estimated from the sectional curvatures of underlying data.Product manifolds enable our approach to better reflect a wide variety of geometric structures on temporal KGs.Besides, to capture the evolutionary dynamics of temporal KGs, we let the entity representations evolve according to a velocity vector defined in the tangent space at each timestamp.We analyze in detail the contribution of geometric spaces to representation learning of temporal KGs and evaluate our model on temporal knowledge graph completion tasks.Extensive experiments on three real-world datasets demonstrate significantly improved performance, indicating that the dynamics of multi-relational graph data can be more properly modeled by the evolution of embeddings on Riemannian manifolds.

Many applications require an understanding of an image that goes beyond the simple detection and classification of its objects. In particular, a great deal of semantic information is carried in the relationships between objects. We have previously shown, that the combination of a visual model and a statistical semantic prior model can improve on the task of mapping images to their associated scene description. In this paper, we review the model and compare it to a novel conditional multi-way model for visual relationship detection, which does not include an explicitly trained visual prior model. We also discuss potential relationships between the proposed methods and memory models of the human brain.