This paper focuses on open-ended video question answering, which aims to find the correct answers from a large answer set in response to a video-related question. This is essentially a multi-label classification task, since a question may have multiple answers. However, due to annotation costs, the labels in existing benchmarks are always extremely insufficient, typically one answer per question. As a result, existing works tend to directly treat all the unlabeled answers as negative labels, leading to limited ability for generalization. In this work, we introduce a simple yet effective ranking distillation framework (RADI) to mitigate this problem without additional manual annotation. RADI employs a teacher model trained with incomplete labels to generate rankings for potential answers, which contain rich knowledge about label priority as well as label-associated visual cues, thereby enriching the insufficient labeling information. To avoid overconfidence in the imperfect teacher model, we further present two robust and parameter-free ranking distillation approaches: a pairwise approach which introduces adaptive soft margins to dynamically refine the optimization constraints on various pairwise rankings, and a listwise approach which adopts sampling-based partial listwise learning to resist the bias in teacher ranking. Extensive experiments on five popular benchmarks consistently show that both our pairwise and listwise RADIs outperform state-of-the-art methods. Further analysis demonstrates the effectiveness of our methods on the insufficient labeling problem.
相關內容
In recent years, the XLogoOnline programming platform has gained popularity among novice learners. It integrates the Logo programming language with visual programming, providing a visual interface for learning computing concepts. However, XLogoOnline offers only a limited set of tasks, which are inadequate for learners to master the computing concepts that require sufficient practice. To address this, we introduce XLogoSyn, a novel technique for synthesizing high-quality tasks for varying difficulty levels. Given a reference task, XLogoSyn can generate practice tasks at varying difficulty levels that cater to the varied needs and abilities of different learners. XLogoSyn achieves this by combining symbolic execution and constraint satisfaction techniques. Our expert study demonstrates the effectiveness of XLogoSyn. We have also deployed synthesized practice tasks into XLogoOnline, highlighting the educational benefits of these synthesized practice tasks.
This article presents a deep reinforcement learning-based approach to tackle a persistent surveillance mission requiring a single unmanned aerial vehicle initially stationed at a depot with fuel or time-of-flight constraints to repeatedly visit a set of targets with equal priority. Owing to the vehicle's fuel or time-of-flight constraints, the vehicle must be regularly refueled, or its battery must be recharged at the depot. The objective of the problem is to determine an optimal sequence of visits to the targets that minimizes the maximum time elapsed between successive visits to any target while ensuring that the vehicle never runs out of fuel or charge. We present a deep reinforcement learning algorithm to solve this problem and present the results of numerical experiments that corroborate the effectiveness of this approach in comparison with common-sense greedy heuristics.
Answering complex logical queries over incomplete knowledge graphs (KGs) is challenging. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex logical reasoning schema over knowledge graphs upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements~(brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Our code and model will be released at GitHub and huggingface soon.
Designing preference elicitation (PE) methodologies that can quickly ascertain a user's top item preferences in a cold-start setting is a key challenge for building effective and personalized conversational recommendation (ConvRec) systems. While large language models (LLMs) constitute a novel technology that enables fully natural language (NL) PE dialogues, we hypothesize that monolithic LLM NL-PE approaches lack the multi-turn, decision-theoretic reasoning required to effectively balance the NL exploration and exploitation of user preferences towards an arbitrary item set. In contrast, traditional Bayesian optimization PE methods define theoretically optimal PE strategies, but fail to use NL item descriptions or generate NL queries, unrealistically assuming users can express preferences with direct item ratings and comparisons. To overcome the limitations of both approaches, we formulate NL-PE in a Bayesian Optimization (BO) framework that seeks to generate NL queries which actively elicit natural language feedback to reduce uncertainty over item utilities to identify the best recommendation. We demonstrate our framework in a novel NL-PE algorithm, PEBOL, which uses Natural Language Inference (NLI) between user preference utterances and NL item descriptions to maintain preference beliefs and BO strategies such as Thompson Sampling (TS) and Upper Confidence Bound (UCB) to guide LLM query generation. We numerically evaluate our methods in controlled experiments, finding that PEBOL achieves up to 131% improvement in MAP@10 after 10 turns of cold start NL-PE dialogue compared to monolithic GPT-3.5, despite relying on a much smaller 400M parameter NLI model for preference inference.
In this paper we look at $k$-stroll, point-to-point orienteering, as well as the deadline TSP problem on graphs with bounded doubling dimension and bounded treewidth and present approximation schemes for them. Given a weighted graph $G=(V,E)$, start node $s\in V$, distances $d:E\rightarrow \mathbb{Q}^+$ and integer $k$. In the $k$-stroll problem the goal is to find a path starting at $s$ of minimum length that visits at least $k$ vertices. The dual problem to $k$-stroll is the rooted orienteering in which instead of $k$ we are given a budget $B$ and the goal is to find a walk of length at most $B$ starting at $s$ that visits as many vertices as possible. In the P2P orienteering we are given start and end nodes $s,t$ for the path. In the deadline TSP we are given a deadline $D(v)$ for each $v\in V$ and the goal is to find a walk starting at $s$ that visits as many vertices as possible before their deadline. The best approximation for rooted or P2P orienteering is $(2+\epsilon)$-approximation [12] and $O(\log n)$-approximation for deadline TSP [3]. There is no known approximation scheme for deadline TSP for any metric (not even trees). Our main result is the first approximation scheme for deadline TSP on metrics with bounded doubling dimension. To do so we first show if $G$ is a metric with doubling dimension $\kappa$ and aspect ratio $\Delta$, there is a $(1+\epsilon)$-approximation that runs in time $n^{O\left(\left(\log\Delta/\epsilon\right)^{2\kappa+1}\right)}$. We then extend these to obtain an approximation scheme for deadline TSP when the distances and deadlines are integer which runs in time $n^{O\left(\left(\log \Delta/\epsilon\right)^{2\kappa+2}\right)}$. For graphs with treewidth $\omega$ we show how to solve $k$-stroll and P2P orienteering exactly in polynomial time and a $(1+\epsilon)$-approximation for deadline TSP in time $n^{O((\omega\log\Delta/\epsilon)^2)}$.
In this paper, we present some enhanced error estimates for augmented subspace methods with the nonconforming Crouzeix-Raviart (CR) element. Before the novel estimates, we derive the explicit error estimates for the case of single eigenpair and multiple eigenpairs based on our defined spectral projection operators, respectively. Then we first strictly prove that the CR element based augmented subspace method exhibits the second-order convergence rate between the two steps of the augmented subspace iteration, which coincides with the practical experimental results. The algebraic error estimates of second order for the augmented subspace method explicitly elucidate the dependence of the convergence rate of the algebraic error on the coarse space, which provides new insights into the performance of the augmented subspace method. Numerical experiments are finally supplied to verify these new estimate results and the efficiency of our algorithms.
Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal Large Language Models (MLLMs). These models can seamlessly integrate visual and textual modalities, both as input and output, while providing a dialogue-based interface and instruction-following capabilities. In this paper, we provide a comprehensive review of recent visual-based MLLMs, analyzing their architectural choices, multimodal alignment strategies, and training techniques. We also conduct a detailed analysis of these models across a wide range of tasks, including visual grounding, image generation and editing, visual understanding, and domain-specific applications. Additionally, we compile and describe training datasets and evaluation benchmarks, conducting comparisons among existing models in terms of performance and computational requirements. Overall, this survey offers a comprehensive overview of the current state of the art, laying the groundwork for future MLLMs.
Aiming at expanding few-shot relations' coverage in knowledge graphs (KGs), few-shot knowledge graph completion (FKGC) has recently gained more research interests. Some existing models employ a few-shot relation's multi-hop neighbor information to enhance its semantic representation. However, noise neighbor information might be amplified when the neighborhood is excessively sparse and no neighbor is available to represent the few-shot relation. Moreover, modeling and inferring complex relations of one-to-many (1-N), many-to-one (N-1), and many-to-many (N-N) by previous knowledge graph completion approaches requires high model complexity and a large amount of training instances. Thus, inferring complex relations in the few-shot scenario is difficult for FKGC models due to limited training instances. In this paper, we propose a few-shot relational learning with global-local framework to address the above issues. At the global stage, a novel gated and attentive neighbor aggregator is built for accurately integrating the semantics of a few-shot relation's neighborhood, which helps filtering the noise neighbors even if a KG contains extremely sparse neighborhoods. For the local stage, a meta-learning based TransH (MTransH) method is designed to model complex relations and train our model in a few-shot learning fashion. Extensive experiments show that our model outperforms the state-of-the-art FKGC approaches on the frequently-used benchmark datasets NELL-One and Wiki-One. Compared with the strong baseline model MetaR, our model achieves 5-shot FKGC performance improvements of 8.0% on NELL-One and 2.8% on Wiki-One by the metric Hits@10.
Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE. However, N-1, 1-N and N-N predictions still remain challenging. In this work, we propose a novel translational distance-based approach for knowledge graph link prediction. The proposed method includes two-folds, first we extend the RotatE from 2D complex domain to high dimension space with orthogonal transforms to model relations for better modeling capacity. Second, the graph context is explicitly modeled via two directed context representations. These context representations are used as part of the distance scoring function to measure the plausibility of the triples during training and inference. The proposed approach effectively improves prediction accuracy on the difficult N-1, 1-N and N-N cases for knowledge graph link prediction task. The experimental results show that it achieves better performance on two benchmark data sets compared to the baseline RotatE, especially on data set (FB15k-237) with many high in-degree connection nodes.
Dense video captioning aims to generate text descriptions for all events in an untrimmed video. This involves both detecting and describing events. Therefore, all previous methods on dense video captioning tackle this problem by building two models, i.e. an event proposal and a captioning model, for these two sub-problems. The models are either trained separately or in alternation. This prevents direct influence of the language description to the event proposal, which is important for generating accurate descriptions. To address this problem, we propose an end-to-end transformer model for dense video captioning. The encoder encodes the video into appropriate representations. The proposal decoder decodes from the encoding with different anchors to form video event proposals. The captioning decoder employs a masking network to restrict its attention to the proposal event over the encoding feature. This masking network converts the event proposal to a differentiable mask, which ensures the consistency between the proposal and captioning during training. In addition, our model employs a self-attention mechanism, which enables the use of efficient non-recurrent structure during encoding and leads to performance improvements. We demonstrate the effectiveness of this end-to-end model on ActivityNet Captions and YouCookII datasets, where we achieved 10.12 and 6.58 METEOR score, respectively.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191