Youliang Yuan, Qiuyang Mang, Jingbang Chen, Hong Wan, Xiaoyuan Liu, Junjielong Xu, Jen-tse Huang, Wenxuan Wang, Wenxiang Jiao, Pinjia He. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

We study the internal dictionary matching (IDM) problem where a dictionary $\mathcal{D}$ containing $d$ substrings of a text $T$ is given, and each query concerns the occurrences of patterns in $\mathcal{D}$ in another substring of $T$. We propose a novel $O(n)$-sized data structure named Basic Substring Structure (BASS) where $n$ is the length of the text $T.$ With BASS, we are able to handle all types of queries in the IDM problem in nearly optimal query and preprocessing time. Specifically, our results include: $\bullet$ The first algorithm that answers the CountDistinct query in $\tilde{O}(1)$ time with $\tilde{O}(n+d)$ preprocessing, where we need to compute the number of distinct patterns that exist in $T[l,r]$. Previously, the best result was $\tilde{O}(m)$ time per query after $\tilde{O}(n^2/m+d)$ or $\tilde{O}(nd/m+d)$ preprocessing, where $m$ is a chosen parameter. $\bullet$ Faster algorithms for two other types of internal queries. We improve the runtime for (1) Occurrence counting (Count) queries to $O(\log n/\log\log n)$ time per query with $O(n+d\sqrt{\log n})$ preprocessing from $O(\log^2 n/\log\log n)$ time per query with $O(n\log n/\log \log n+d\log^{3/2} n)$ preprocessing. (2) Distinct pattern reporting (ReportDistinct) queries to $O(1+|\text{output}|)$ time per query from $O(\log n+|\text{output}|)$ per query. In addition, we match the optimal runtime in the remaining two types of queries, pattern existence (Exists), and occurrence reporting (Report). We also show that BASS is more generally applicable to other internal query problems.

Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LLMs to recommendation scenarios, and utilize beam search during inference to efficiently retrieve B top-ranked recommended items. However, we identify a critical training-inference inconsistency: while SFT optimizes the overall probability of positive items, it does not guarantee that such items will be retrieved by beam search even if they possess high overall probabilities. Due to the greedy pruning mechanism, beam search can prematurely discard a positive item once its prefix probability is insufficient.

Recommendation systems (RS) aim to retrieve the top-K items most relevant to users, with metrics such as Precision@K and Recall@K commonly used to assess effectiveness. The architecture of an RS model acts as an inductive bias, shaping the patterns the model is inclined to learn. In recent years, numerous recommendation architectures have emerged, spanning traditional matrix factorization, deep neural networks, and graph neural networks. However, their designs are often not explicitly aligned with the top-K objective, thereby limiting their effectiveness. To address this limitation, we propose TopKGAT, a novel recommendation architecture directly derived from a differentiable approximation of top-K metrics. The forward computation of a single TopKGAT layer is intrinsically aligned with the gradient ascent dynamics of the Precision@K metric, enabling the model to naturally improve top-K recommendation accuracy. Structurally, TopKGAT resembles a graph attention network and can be implemented efficiently. Extensive experiments on four benchmark datasets demonstrate that TopKGAT consistently outperforms state-of-the-art baselines. The code is available at https://github.com/StupidThree/TopKGAT.

We study learning-augmented binary search trees (BSTs) via Treaps with carefully designed priorities. The result is a simple search tree in which the depth of each item $x$ is determined by its predicted weight $w_x$. Specifically, each item $x$ is assigned a composite priority of $-\lfloor\log\log(1/w_x)\rfloor + U(0, 1)$ where $U(0, 1)$ is the uniform random variable. By choosing $w_x$ as the relative frequency of $x$, the resulting search trees achieve static optimality. This approach generalizes the recent learning-augmented BSTs [Lin-Luo-Woodruff ICML`22], which only work for Zipfian distributions, by extending them to arbitrary input distributions. Furthermore, we demonstrate that our method can be generalized to a B-Tree data structure using the B-Treap approach [Golovin ICALP'09]. Our search trees are also capable of leveraging localities in the access sequence through online self-reorganization, thereby achieving the working-set property. Additionally, they are robust to prediction errors and support dynamic operations, such as insertions, deletions, and prediction updates. We complement our analysis with an empirical study, demonstrating that our method outperforms prior work and classic data structures.

Bipartite graphs are ubiquitous in many domains, e.g., e-commerce platforms, social networks, and academia, by modeling interactions between distinct entity sets. Within these graphs, the butterfly motif, a complete 2×2 biclique, represents the simplest yet significant subgraph structure, crucial for analyzing complex network patterns. Counting the butterflies offers significant benefits across various applications, including community analysis and recommender systems. Additionally, the temporal dimension of bipartite graphs, where edges activate within specific time frames, introduces the concept of historical butterfly counting, i.e., counting butterflies within a given time interval. This temporal analysis sheds light on the dynamics and evolution of network interactions, offering new insights into their mechanisms. Despite its importance, no existing algorithm can efficiently solve the historical butterfly counting task. To address this, we design two novel indices whose memory footprints are dependent on #butterflies and #wedges, respectively. Combining these indices, we propose a graph structure-aware indexing approach that significantly reduces memory usage while preserving exceptional query speed. To further reduce the index size and boost the query efficiency, we design an index compression strategy, enabling the fast, high-quality, and unbiased approximation of historical butterfly counts. We theoretically prove that our approach is particularly advantageous on power-law graphs, a common characteristic of real-world bipartite graphs, by surpassing traditional complexity barriers for general graphs. Extensive experiments reveal that our query algorithms outperform existing methods by up to five magnitudes, effectively balancing speed with manageable memory requirements.

Signed networks, characterized by edges labeled as either positive or negative, offer nuanced insights into interaction dynamics beyond the capabilities of unsigned graphs. Central to this is the task of identifying the maximum balanced subgraph, crucial for applications like polarized community detection in social networks and portfolio analysis in finance. Traditional models, however, are limited by an assumption of perfect partitioning, which fails to mirror the complexities of real-world data. Addressing this gap, we introduce an innovative generalized balanced subgraph model that incorporates tolerance for imbalance. Our proposed region-based heuristic algorithm, tailored for this NP -hard problem, strikes a balance between low time complexity and high-quality outcomes. Comparative experiments validate its superior performance against leading solutions, delivering enhanced effectiveness (notably larger subgraph sizes) and efficiency (achieving up to 100× speedup) in both traditional and generalized contexts.

We design the first dynamic distance oracles for interval graphs, which are intersection graphs of a set of intervals on the real line, and for proper interval graphs, which are intersection graphs of a set of intervals in which no interval is properly contained in another. For proper interval graphs, we design a linear space data structure which supports distance queries (computing the distance between two query vertices) and vertex insertion or deletion in O(lg⁡n) worst-case time, where n is the number of vertices currently in G. Under incremental (insertion only) or decremental (deletion only) settings in general interval graphs, we design linear space data structures that support distance queries in O(lg⁡n) worst-case time and vertex insertion or deletion in O(lg⁡n) amortized time, where n is the maximum number of vertices in the graph. Under fully dynamic settings in general interval graphs, we design a data structure that represents an interval graph G in O(n) words of space to support distance queries in O(nlg⁡n/S(n)) worst-case time and vertex insertion or deletion in O(S(n)+lg⁡n) worst-case time, where n is the number of vertices currently in G and S(n) is an arbitrary function that satisfies S(n)=Ω(1) and S(n)=O(n). This implies an O(n)-word solution with O(nlg⁡n)-time support for both distance queries and updates. All four data structures can answer shortest path queries by reporting the vertices in the shortest path between two query vertices in O(lg⁡n) worst-case time per vertex. We also study the hardness of supporting distance queries under updates over an intersection graph of 3D axis-aligned line segments, which generalizes our problem to 3D. Finally, we solve the problem of computing the diameter of a dynamic connected interval graph.

Recommendation from implicit feedback is a highly challenging task due to the lack of the reliable observed negative data. A popular and effective approach for implicit recommendation is to treat unobserved data as negative but downweight their confidence. Naturally, how to assign confidence weights and how to handle the large number of the unobserved data are two key problems for implicit recommendation models. However, existing methods either pursuit fast learning by manually assigning simple confidence weights, which lacks flexibility and may create empirical bias in evaluating user's preference; or adaptively infer personalized confidence weights but suffer from low efficiency.To achieve both adaptive weights assignment and efficient model learning, we propose a fast adaptively weighted matrix factorization (FAWMF) based on variational auto-encoder. The personalized data confidence weights are adaptively assigned with a parameterized neural network (function) and the network can be inferred from the data. Further, to support fast and stable learning of FAWMF, a new specific batch-based learning algorithm fBGD has been developed, which trains on all feedback data but its complexity is linear to the number of observed data. Extensive experiments on real-world datasets demonstrate the superiority of the proposed FAWMF and its learning algorithm fBGD.