Traffic light control plays a crucial role in intelligent transportation systems. This paper introduces Temporal Difference-Aware Graph Convolutional Reinforcement Learning (TeDA-GCRL), a decentralized RL-based method for efficient multi-intersection traffic signal control. Specifically, we put forward a new graph architecture using each lane as a node for considering intersection relations. Additionally, we propose two new rewards by considering temporal information, namely Temporal-Aware Pressure on Incoming Lanes (TAPIL) and Temporal-Aware Action Consistency (TAAC), which enhance learning efficiency and time-interval sensitivity. Experimental results on five datasets show the superiority of TeDA-GCRL over state-of-the-art methods by at least 9.5% in average travel time.

As the impact of social media gradually escalates, people are more likely to be exposed to indistinguishable fake news.Therefore, numerous studies have attempted to detect rumors on social media by analyzing the textual content and propagation paths.However, fewer works on rumor detection tasks consider the malicious attacks commonly observed at response level.Moreover, existing detection models have poor interpretability.To address these issues, we propose a novel framework named Defend-And-Summarize (DAS) based on the concept that responses sharing similar opinions should exhibit similar features.Specifically, DAS filters out the attack responses and summarizes the responsive posts of each conversation thread in both extractive and abstractive ways to provide multi-perspective prediction explanations.Furthermore, we enhance our detection architecture with the transformer and Bi-directional Graph Convolutional Networks.Experiments on three public datasets, i.e., RumorEval2019, Twitter15, and Twitter16, demonstrate that our DAS defends against malicious attacks and provides prediction explanations, and the proposed detection model achieves state-of-the-art. 1

Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstrations presented in the inputs. Recent works promote this ability in the vision-language domain by incorporating visual information into large language models that can already make in-context predictions. However, these methods could inherit issues in the language domain, such as template sensitivity and hallucination. Also, the scale of these language models raises a significant demand for computations, making learning and operating these models resource-intensive. To this end, we raise a question: "How can we enable in-context learning without relying on the intrinsic in-context ability of large language models?". To answer it, we propose a succinct and general framework, Self-supervised IN-Context learning (SINC), that introduces a meta-model to learn on self-supervised prompts consisting of tailored demonstrations. The learned models can be transferred to downstream tasks for making in-context predictions on-the-fly. Extensive experiments show that SINC outperforms gradient-based methods in various vision-language tasks under few-shot settings. Furthermore, the designs of SINC help us investigate the benefits of in-context learning across different tasks, and the analysis further reveals the essential components for the emergence of in-context learning in the vision-language domain.

Review-Based Recommender Systems (RBRS) have attracted increasing research interest due to their ability to alleviate well-known cold-start problems. RBRS utilizes reviews to construct the user and items representations. However, in this paper, we argue that such a reliance on reviews may instead expose systems to the risk of being shilled. To explore this possibility, in this paper, we propose the first generation-based model for shilling attacks against RBRSs. Specifically, we learn a fake review generator through reinforcement learning, which maliciously promotes items by forcing prediction shifts after adding generated reviews to the system. By introducing the auxiliary rewards to increase text fluency and diversity with the aid of pre-trained language models and aspect predictors, the generated reviews can be effective for shilling with high fidelity. Experimental results demonstrate that the proposed framework can successfully attack three different kinds of RBRSs on the Amazon corpus with three domains and Yelp corpus. Furthermore, human studies also show that the generated reviews are fluent and informative. Finally, equipped with Attack Review Generators (ARGs), RBRSs with adversarial training are much more robust to malicious reviews.

Referring Expression Comprehension (REC) aims to locate a specific object within an image by interpreting a referring expression articulated in natural language. This task comprises two essential branches: understanding and localizing. The former entails processing cognitive information from multimodal data, while the latter involves realizing the predictions in the perceptive visual space. Although various advanced approaches have been developed for each of these branches separately, existing REC approaches are unable to effectively leverage them due to the specific designs of architectures or objectives for REC, which bind understanding and localizing inseparably. To overcome this challenge, we propose the Decoupling-Cooperative Framework (DCF). The decoupling scheme in DCF enables us to utilize up-to-date methods for understanding and localizing with minimal constraints. Meanwhile, the proposed cooperative modules enable better integration of the strengths from both branches to achieve further enhancements. Extensive experiments demonstrate that DCF achieves state-of-the-art performance across four benchmarks, thus highlighting the generalizability of DCF.

Abstract Personalized Headline Generation aims to generate unique headlines tailored to users’ browsing history. In this task, understanding user preferences from click history and incorporating them into headline generation pose challenges. Existing approaches typically rely on predefined styles as control codes, but personal style lacks explicit definition or enumeration, making it difficult to leverage traditional techniques. To tackle these challenges, we propose General Then Personal (GTP), a novel framework comprising user modeling, headline generation, and customization. We train the framework using tailored designs that emphasize two central ideas: (a) task decoupling and (b) model pre-training. With the decoupling mechanism separating the task into generation and customization, two mechanisms, i.e., information self-boosting and mask user modeling, are further introduced to facilitate the training and text control. Additionally, we introduce a new evaluation metric to address existing limitations. Extensive experiments conducted on the PENS dataset, considering both zero-shot and few-shot scenarios, demonstrate that GTP outperforms state-of-the-art methods. Furthermore, ablation studies and analysis emphasize the significance of decoupling and pre-training. Finally, the human evaluation validates the effectiveness of our approaches.1

Neural abstractive summarization has been widely studied and achieved great success with large-scale corpora. However, the considerable cost of annotating data motivates the need for learning strategies under low-resource settings. In this paper, we investigate the problems of learning summarizers with only few examples and propose corresponding methods for improvements. First, typical transfer learning methods are prone to be affected by data properties and learning objectives in the pretext tasks. Therefore, based on pretrained language models, we further present a meta learning framework to transfer few-shot learning processes from source corpora to the target corpus. Second, previous methods learn from training examples without decomposing thecontentandpreference. The generated summaries could therefore be constrained by the preference bias in the training set, especially under low-resource settings. As such, we propose decomposing the contents and preferences during learning through the parameter modulation, which enables control over preferences during inference. Third, given a target application, specifying required preferences could be non-trivial because the preferences may be difficult to derive through observations. Therefore, we propose a novel decoding method to automatically estimate suitable preferences and generate corresponding summary candidates from the few training examples. Extensive experiments demonstrate that our methods achieve state-of-the-art performance on six diverse corpora with 30.11%/33.95%/27.51% and 26.74%/31.14%/24.48% average improvements on ROUGE-1/2/L under 10- and 100-example settings.

A notable challenge in Multi-Document Summarization (MDS) is the extremely-long length of the input.In this paper, we present an extract-then-abstract Transformer framework to overcome the problem.Specifically, we leverage pre-trained language models to construct a hierarchical extractor for salient sentence selection across documents and an abstractor for rewriting the selected contents as summaries.However, learning such a framework is challenging since the optimal contents for the abstractor are generally unknown.Previous works typically create pseudo extraction oracle to enable the supervised learning for both the extractor and the abstractor.Nevertheless, we argue that the performance of such methods could be restricted due to the insufficient information for prediction and inconsistent objectives between training and testing.To this end, we propose a loss weighting mechanism that makes the model aware of the unequal importance for the sentences not in the pseudo extraction oracle, and leverage the fine-tuned abstractor to generate summary references as auxiliary signals for learning the extractor.Moreover, we propose a reinforcement learning method that can efficiently apply to the extractor for harmonizing the optimization between training and testing.Experiment results show that our framework substantially outperforms strong baselines with comparable model sizes and achieves the best results on the Multi-News, Multi-XScience, and WikiCatSum corpora. 1

With the rapid proliferation of online media sources and published news, headlines have become increasingly important for attracting readers to news articles, since users may be overwhelmed with the massive information. In this paper, we generate inspired headlines that preserve the nature of news articles and catch the eye of the reader simultaneously. The task of inspired headline generation can be viewed as a specific form of Headline Generation (HG) task, with the emphasis on creating an attractive headline from a given news article. To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG). PORL-HG exploits the extractive-abstractive architecture with 1) Popular Topic Attention (PTA) for guiding the extractor to select the attractive sentence from the article and 2) a popularity predictor for guiding the abstractor to rewrite the attractive sentence. Moreover, since the sentence selection of the extractor is not differentiable, techniques of reinforcement learning (RL) are utilized to bridge the gap with rewards obtained from a popularity score predictor. Through quantitative and qualitative experiments, we show that the proposed PORL-HG significantly outperforms the state-of-the-art headline generation models in terms of attractiveness evaluated by both human (71.03%) and the predictor (at least 27.60%), while the faithfulness of PORL-HG is also comparable to the state-of-the-art generation model.