This paper addresses the challenge of discontinuity in goal-achievement capabilities observed in Goal-conditioned Reinforcement Learning (GCRL) algorithms. Through a theoretical analysis, we identify that the reuse of successful trajectories or policies during training can aid in achieving adjacent goals of achievable goals. However, the policy discrepancy between achievable and adjacent goals must be carefully managed to avoid both overly trivial and excessively large differences, which can respectively hinder policy performance. To tackle this issue, we propose a margin-based policy self-regularization approach that optimizes the policy discrepancies between adjacent desired goals to a minimal acceptable threshold. This method can be integrated into popular GCRL algorithms, such as GC-SAC, HER, and GC-PPO. Systematic evaluations across two robotic arm control tasks and a complex fixed-wing aircraft control task demonstrate that our approach significantly improves the continuity of goal-achievement abilities of GCRL algorithms, thereby enhancing their overall performance.

MOTIVATION: Generative models have demonstrated considerable promise in de novo protein design. Traditional approaches typically focus on either sequence or structure in isolation, limiting the capacity to explore the intricate sequence-structure landscape and achieve optimal designs. However, joint protein sequence and structure co-design remains a largely underexplored challenge. RESULTS: We present CoFlow, a discrete model for protein co-design from scratch or given constraints. CoFlow employs a joint discrete flow and integrates a multi-modal protein masked language model to facilitate co-design in the discrete space. Comprehensive experiments demonstrate that CoFlow outperforms previous design methods across multiple evaluation metrics. Notably, CoFlow achieves a consistency approximately eight times higher than that of ESM3 in unconditional generation. Moreover, CoFlow exhibits competitive performance in conditional generation tasks, including motif-scaffolding, protein folding, and inverse folding. AVAILABILITY AND IMPLEMENTATION: The source code of CoFlow, including data preprocessing and model, is available at https://github.com/LtECoD/CoFlow and https://zenodo.org/records/14842367. (DOI: 10.5281/zenodo.14842367).

Protein-to-protein interaction (PPI) prediction aims to predict whether two given proteins interact or not. Compared with traditional experimental methods of high cost and low efficiency, the current deep learning based approach makes it possible to discover massive potential PPIs from large-scale databases. However, deep PPI prediction models perform poorly on unseen species, as their proteins are not in the training set. Targetting on this issue, the paper first proposes PPITrans, a Transformer based PPI prediction model that exploits a language model pre-trained on proteins to conduct binary PPI prediction. To validate the effectiveness on unseen species, PPITrans is trained with Human PPIs and tested on PPIs of other species. Experimental results show that PPITrans significantly outperforms the previous state-of-the-art on various metrics, especially on PPIs of unseen species. For example, the AUPR improves 0.339 absolutely on Fly PPIs. Aiming to explore the knowledge learned by PPITrans from PPI data, this paper also designs a series of probes belonging to three categories. Their results reveal several interesting findings, like that although PPITrans cannot capture the spatial structure of proteins, it can obtain knowledge of PPI type and binding affinity, learning more than binary PPI.

Semantic networks, exemplified by the knowledge graph, serve as a means to represent knowledge by leveraging the structure of a graph. While the knowledge graph exhibits promising potential in the field of natural language processing, it suffers from incompleteness. This article focuses on the task of completing knowledge graphs by predicting linkages between entities, which is fundamental yet critical. Traditional methods based on translational distance struggle when dealing with unseen entities. In contrast, semantic matching presents itself as a potential solution due to its ability to handle such cases. However, semantic matching-based approaches necessitate large-scale datasets for effective training, which are typically unavailable in practical scenarios, hindering their competitive performance. To address this challenge, we propose a novel architecture for knowledge graphs known as LP-BERT, which incorporates a language model. LP-BERT consists of two primary stages: multi-task pre-training and knowledge graph fine-tuning. During the pre-training phase, the model acquires relationship information from triples by predicting either entities or relations through three distinct tasks. In the fine-tuning phase, we introduce a batch-based triple-style negative sampling technique inspired by contrastive learning. This method significantly increases the proportion of negative sampling while maintaining a nearly unchanged training time. Furthermore, we propose a novel data augmentation approach that leverages the inverse relationship of triples to enhance both the performance and robustness of the model. To demonstrate the effectiveness of our proposed framework, we conduct extensive experiments on three widely used knowledge graph datasets: WN18RR, FB15k-237, and UMLS. The experimental results showcase the superiority of our methods, with LP-BERT achieving state-of-the-art performance on the WN18RR and FB15k-237 datasets.

As a critical component for online advertising and marketing, click-through rate (CTR) prediction has drawn lots of attention from both industry and academia. Recently, deep learning has become the mainstream methodological choice for CTR. Despite sustainable efforts have been made, existing approaches still pose several challenges. On the one hand, high-order interaction between the features is under-explored. On the other hand, high-order interactions may neglect the semantic information from the low-order fields. In this paper, we proposed a novel prediction method, named FINT, that employs the Field-aware INTeraction layer which explicitly captures high-order feature interactions while retaining the low-order field information. To empirically investigate the effectiveness and robustness of the FINT, we perform extensive experiments on the three realistic databases: KDD2012, Criteo and Avazu. The obtained results demonstrate that the FINT can significantly improve the performance compared to the existing methods, without increasing the amount of computation required. Moreover, the proposed method brought about 2.72% increase to the advertising revenue of iQIYI, a big online video app through A/B testing. To better promote the research in CTR field, we released our code as well as reference implementation at: https://github.com/zhishan01/FINT.

Transcribing structural data into readable text (data-to-text) is a fundamental language generation task. One of its challenges is to plan the input records for text realization. Recent works tackle this problem with a static planner, which performs record planning in advance for text realization. However, they cannot revise plans to cope with unexpected realized text and require golden plans for supervised training. To address these issues, we first propose a model that contains a dynamic planner. It decomposes text generation into two alternately procedures, record planning and text realization. We also devise a novel likelihood-driven training strategy for the planner. This strategy exploits sentence likelihood to select input records, which requires no annotated plan. Besides, we design a metric based on the set similarity to evaluate the quality of predicted plans. We conduct comprehensive experiments on two data-to-text datasets, E2E and EPW. Our best model considerably outperforming previous works on both text metrics and plan metrics. The likelihood-driven strategy also exhibits competitiveness for training the dynamic planner.

Event extraction is an important subtask of information extraction. The goal of event extraction is to quickly extract events of a specified type from a large amount of textual information. Many excellent models and algorithms have been proposed since ACE released the event extraction task in 2005. Most of them are based on the dataset published by ACE and have contributed to the accuracy of event extraction to a certain extent. In practical applications, the processing object of the event extraction task is large-scale text data. However, as far as we know, there is currently no effective model for using multiple computers for event extraction. In this paper, we propose a model for event extraction based on inter-cloud computing technology. The experimental results prove that our method reduces the time consumption and also gets better accuracy than advanced models.

Traditional approaches to the task of ACE event extraction usually depend on manually annotated data, which is often laborious to create and limited in size. Therefore, in addition to the difficulty of event extraction itself, insufficient training data hinders the learning process as well. To promote event extraction, we first propose an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles. Moreover, to address the problem of insufficient training data, we propose a method to automatically generate labeled data by editing prototypes and screen out generated samples by ranking the quality. Experiments on the ACE2005 dataset demonstrate that our extraction model can surpass most existing extraction methods. Besides, incorporating our generation method exhibits further significant improvement. It obtains new state-of-the-art results on the event extraction task, including pushing the F1 score of trigger classification to 81.1%, and the F1 score of argument classification to 58.9%.